extmod: Add ubinascii.unhexlify

This also pulls out hex_digit from py/lexer.c and makes unichar_hex_digit

docs/library/ubinascii.rst

@@ -13,3 +13,8 @@ Functions
 .. function:: hexlify(data)
 
    Convert binary data to hexadecimal representation. Return bytes string.
+
+.. function:: unhexlify(data)
+
+   Convert hexadecimal data to binary representation. Return bytes string.
+   (i.e. inverse of hexlify)

extmod/modubinascii.c

@@ -35,6 +35,8 @@
 #if MICROPY_PY_UBINASCII
 
 STATIC mp_obj_t mod_binascii_hexlify(mp_uint_t n_args, const mp_obj_t *args) {
+    // Second argument is for an extension to allow a separator to be used
+    // between values.
     (void)n_args;
     mp_buffer_info_t bufinfo;
     mp_get_buffer_raise(args[0], &bufinfo, MP_BUFFER_READ);
@@ -58,10 +60,39 @@ STATIC mp_obj_t mod_binascii_hexlify(mp_uint_t n_args, const mp_obj_t *args) {
 }
 MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(mod_binascii_hexlify_obj, 1, 2, mod_binascii_hexlify);
 
+STATIC mp_obj_t mod_binascii_unhexlify(mp_obj_t data) {
+    mp_buffer_info_t bufinfo;
+    mp_get_buffer_raise(data, &bufinfo, MP_BUFFER_READ);
+
+    if ((bufinfo.len & 1) != 0) {
+        nlr_raise(mp_obj_new_exception_msg_varg(&mp_type_ValueError, "odd-length string"));
+    }
+    vstr_t vstr;
+    vstr_init_len(&vstr, bufinfo.len / 2);
+    byte *in = bufinfo.buf, *out = (byte*)vstr.buf;
+    byte hex_byte = 0;
+    for (mp_uint_t i = bufinfo.len; i--;) {
+        byte hex_ch = *in++;
+        if (unichar_isxdigit(hex_ch)) {
+            hex_byte += unichar_xdigit_value(hex_ch);
+        } else {
+            nlr_raise(mp_obj_new_exception_msg_varg(&mp_type_ValueError, "non-hex digit found"));
+        }
+        if (i & 1) {
+            hex_byte <<= 4;
+        } else {
+            *out++ = hex_byte;
+            hex_byte = 0;
+        }
+    }
+    return mp_obj_new_str_from_vstr(&mp_type_bytes, &vstr);
+}
+MP_DEFINE_CONST_FUN_OBJ_1(mod_binascii_unhexlify_obj, mod_binascii_unhexlify);
+
 STATIC const mp_map_elem_t mp_module_binascii_globals_table[] = {
     { MP_OBJ_NEW_QSTR(MP_QSTR___name__), MP_OBJ_NEW_QSTR(MP_QSTR_ubinascii) },
     { MP_OBJ_NEW_QSTR(MP_QSTR_hexlify), (mp_obj_t)&mod_binascii_hexlify_obj },
-//    { MP_OBJ_NEW_QSTR(MP_QSTR_unhexlify), (mp_obj_t)&mod_binascii_unhexlify_obj },
+    { MP_OBJ_NEW_QSTR(MP_QSTR_unhexlify), (mp_obj_t)&mod_binascii_unhexlify_obj },
 //    { MP_OBJ_NEW_QSTR(MP_QSTR_a2b_base64), (mp_obj_t)&mod_binascii_a2b_base64_obj },
 //    { MP_OBJ_NEW_QSTR(MP_QSTR_b2a_base64), (mp_obj_t)&mod_binascii_b2a_base64_obj },
 };

py/lexer.c

@@ -261,16 +261,6 @@ STATIC const char *tok_kw[] = {
     "__debug__",
 };
 
-STATIC mp_uint_t hex_digit(unichar c) {
-    // c is assumed to be hex digit
-    mp_uint_t n = c - '0';
-    if (n > 9) {
-        n &= ~('a' - 'A');
-        n -= ('A' - ('9' + 1));
-    }
-    return n;
-}
-
 // This is called with CUR_CHAR() before first hex digit, and should return with
 // it pointing to last hex digit
 // num_digits must be greater than zero
@@ -282,7 +272,7 @@ STATIC bool get_hex(mp_lexer_t *lex, mp_uint_t num_digits, mp_uint_t *result) {
         if (!unichar_isxdigit(c)) {
             return false;
         }
-        num = (num << 4) + hex_digit(c);
+        num = (num << 4) + unichar_xdigit_value(c);
     }
     *result = num;
     return true;

py/misc.h

@@ -127,6 +127,7 @@ bool unichar_isupper(unichar c);
 bool unichar_islower(unichar c);
 unichar unichar_tolower(unichar c);
 unichar unichar_toupper(unichar c);
+mp_uint_t unichar_xdigit_value(unichar c);
 mp_uint_t unichar_charlen(const char *str, mp_uint_t len);
 #define UTF8_IS_NONASCII(ch) ((ch) & 0x80)
 #define UTF8_IS_CONT(ch) (((ch) & 0xC0) == 0x80)

py/qstrdefs.h

@@ -584,6 +584,7 @@ Q(sha256)
 #if MICROPY_PY_UBINASCII
 Q(ubinascii)
 Q(hexlify)
+Q(unhexlify)
 #endif
 
 #if MICROPY_PY_MACHINE

py/unicode.c

@@ -169,3 +169,13 @@ unichar unichar_toupper(unichar c) {
     }
     return c;
 }
+
+mp_uint_t unichar_xdigit_value(unichar c) {
+    // c is assumed to be hex digit
+    mp_uint_t n = c - '0';
+    if (n > 9) {
+        n &= ~('a' - 'A');
+        n -= ('A' - ('9' + 1));
+    }
+    return n;
+}

tests/extmod/ubinascii_unhexlify.py

+try:
+    import ubinascii as binascii
+except ImportError:
+    import binascii
+
+print(binascii.unhexlify(b'0001020304050607'))
+print(binascii.unhexlify(b'08090a0b0c0d0e0f'))
+print(binascii.unhexlify(b'7f80ff'))
+print(binascii.unhexlify(b'313233344142434461626364'))