py: Add MICROPY_QSTR_BYTES_IN_LEN config option, defaulting to 1.

This new config option sets how many fixed-number-of-bytes to use to
store the length of each qstr.  Previously this was hard coded to 2,
but, as per issue #1056, this is considered overkill since no-one
needs identifiers longer than 255 bytes.

With this patch the number of bytes for the length is configurable, and
defaults to 1 byte.  The configuration option filters through to the
makeqstrdata.py script.

Code size savings going from 2 to 1 byte:
- unix x64 down by 592 bytes
- stmhal down by 1148 bytes
- bare-arm down by 284 bytes

Also has RAM savings, and will be slightly more efficient in execution.

4 files changed, 41 insertions, 17 deletions

diff --git a/py/makeqstrdata.py b/py/makeqstrdata.py
index c8e998ed11..48fd9e09d4 100644
--- a/py/makeqstrdata.py
+++ b/py/makeqstrdata.py
@@ -73,16 +73,27 @@ def do_work(infiles):
                 # add the qstr to the list, with order number to retain original order in file
                 qstrs[ident] = (len(qstrs), ident, qstr)
 
-    # process the qstrs, printing out the generated C header file
+    # get config variables
+    cfg_bytes_len = int(qcfgs['BYTES_IN_LEN'])
+    cfg_max_len = 1 << (8 * cfg_bytes_len)
+
+    # print out the starte of the generated C header file
     print('// This file was automatically generated by makeqstrdata.py')
     print('')
+
     # add NULL qstr with no hash or data
-    print('QDEF(MP_QSTR_NULL, (const byte*)"\\x00\\x00\\x00\\x00" "")')
+    print('QDEF(MP_QSTR_NULL, (const byte*)"\\x00\\x00%s" "")' % ('\\x00' * cfg_bytes_len))
+
+    # go through each qstr and print it out
     for order, ident, qstr in sorted(qstrs.values(), key=lambda x: x[0]):
         qhash = compute_hash(qstr)
         qlen = len(qstr)
         qdata = qstr.replace('"', '\\"')
-        print('QDEF(MP_QSTR_%s, (const byte*)"\\x%02x\\x%02x\\x%02x\\x%02x" "%s")' % (ident, qhash & 0xff, (qhash >> 8) & 0xff, qlen & 0xff, (qlen >> 8) & 0xff, qdata))
+        if qlen >= cfg_max_len:
+            print('qstr is too long:', qstr)
+            assert False
+        qlen_str = ('\\x%02x' * cfg_bytes_len) % tuple(qlen.to_bytes(cfg_bytes_len, 'little'))
+        print('QDEF(MP_QSTR_%s, (const byte*)"\\x%02x\\x%02x%s" "%s")' % (ident, qhash & 0xff, (qhash >> 8) & 0xff, qlen_str, qdata))
 
     return True
 
diff --git a/py/mpconfig.h b/py/mpconfig.h
index dcc116daf2..541f7c75a5 100644
--- a/py/mpconfig.h
+++ b/py/mpconfig.h
@@ -112,6 +112,13 @@
 #define MICROPY_MODULE_DICT_SIZE (1)
 #endif
 
+// Number of bytes used to store qstr length
+// Dictates hard limit on maximum Python identifier length, but 1 byte
+// (limit of 255 bytes in an identifier) should be enough for everyone
+#ifndef MICROPY_QSTR_BYTES_IN_LEN
+#define MICROPY_QSTR_BYTES_IN_LEN (1)
+#endif
+
 /*****************************************************************************/
 /* Micro Python emitters                                                     */
 
diff --git a/py/qstr.c b/py/qstr.c
index bb31a08b39..c244738a5e 100644
--- a/py/qstr.c
+++ b/py/qstr.c
@@ -50,9 +50,17 @@
 //  - \0 terminated (for now, so they can be printed using printf)
 
 #define Q_GET_HASH(q)   ((q)[0] | ((q)[1] << 8))
-#define Q_GET_ALLOC(q)  (4 + Q_GET_LENGTH(q) + 1)
-#define Q_GET_LENGTH(q) ((q)[2] | ((q)[3] << 8))
-#define Q_GET_DATA(q)   ((q) + 4)
+#define Q_GET_ALLOC(q)  (2 + MICROPY_QSTR_BYTES_IN_LEN + Q_GET_LENGTH(q) + 1)
+#define Q_GET_DATA(q)   ((q) + 2 + MICROPY_QSTR_BYTES_IN_LEN)
+#if MICROPY_QSTR_BYTES_IN_LEN == 1
+    #define Q_GET_LENGTH(q) ((q)[2])
+    #define Q_SET_LENGTH(q, len) do { (q)[2] = (len); } while (0)
+#elif MICROPY_QSTR_BYTES_IN_LEN == 2
+    #define Q_GET_LENGTH(q) ((q)[2] | ((q)[3] << 8))
+    #define Q_SET_LENGTH(q, len) do { (q)[2] = (len); (q)[3] = (len) >> 8; } while (0)
+#else
+    #error unimplemented qstr length decoding
+#endif
 
 // this must match the equivalent function in makeqstrdata.py
 mp_uint_t qstr_compute_hash(const byte *data, mp_uint_t len) {
@@ -143,23 +151,21 @@ qstr qstr_from_strn(const char *str, mp_uint_t len) {
     qstr q = qstr_find_strn(str, len);
     if (q == 0) {
         mp_uint_t hash = qstr_compute_hash((const byte*)str, len);
-        byte *q_ptr = m_new(byte, 4 + len + 1);
+        byte *q_ptr = m_new(byte, 2 + MICROPY_QSTR_BYTES_IN_LEN + len + 1);
         q_ptr[0] = hash;
         q_ptr[1] = hash >> 8;
-        q_ptr[2] = len;
-        q_ptr[3] = len >> 8;
-        memcpy(q_ptr + 4, str, len);
-        q_ptr[4 + len] = '\0';
+        Q_SET_LENGTH(q_ptr, len);
+        memcpy(q_ptr + 2 + MICROPY_QSTR_BYTES_IN_LEN, str, len);
+        q_ptr[2 + MICROPY_QSTR_BYTES_IN_LEN + len] = '\0';
         q = qstr_add(q_ptr);
     }
     return q;
 }
 
 byte *qstr_build_start(mp_uint_t len, byte **q_ptr) {
-    assert(len <= 65535);
-    *q_ptr = m_new(byte, 4 + len + 1);
-    (*q_ptr)[2] = len;
-    (*q_ptr)[3] = len >> 8;
+    assert(len < (1 << (8 * MICROPY_QSTR_BYTES_IN_LEN)));
+    *q_ptr = m_new(byte, 2 + MICROPY_QSTR_BYTES_IN_LEN + len + 1);
+    Q_SET_LENGTH(*q_ptr, len);
     return Q_GET_DATA(*q_ptr);
 }
 
@@ -170,7 +176,7 @@ qstr qstr_build_end(byte *q_ptr) {
         mp_uint_t hash = qstr_compute_hash(Q_GET_DATA(q_ptr), len);
         q_ptr[0] = hash;
         q_ptr[1] = hash >> 8;
-        q_ptr[4 + len] = '\0';
+        q_ptr[2 + MICROPY_QSTR_BYTES_IN_LEN + len] = '\0';
         q = qstr_add(q_ptr);
     } else {
         m_del(byte, q_ptr, Q_GET_ALLOC(q_ptr));
diff --git a/py/qstrdefs.h b/py/qstrdefs.h
index 514116b65d..71a523c2d6 100644
--- a/py/qstrdefs.h
+++ b/py/qstrdefs.h
@@ -30,7 +30,7 @@
 // That is, they are in ROM and you can reference them simply as MP_QSTR_xxxx.
 
 // qstr configuration passed to makeqstrdata.py of the form QCFG(key, value)
-//QCFG(somekey, somevalue)
+QCFG(BYTES_IN_LEN, MICROPY_QSTR_BYTES_IN_LEN)
 
 Q()
 Q(*)