py/qstr: Separate hash and len from string data.

This allows the compiler to merge strings: e.g. "update",
"difference_update" and "symmetric_difference_update" will all point to the
same memory.

No functional change.

The size reduction depends on the number of qstrs in the build.  The change
this commit brings is:

   bare-arm:    -4 -0.007%
minimal x86:  +150 +0.092% [incl +48(data)]
   unix x64:  -608 -0.118%
unix nanbox:  -572 -0.126% [incl +32(data)]
      stm32: -1392 -0.352% PYBV10
     cc3200:  -448 -0.244%
    esp8266: -1208 -0.173% GENERIC
      esp32: -1028 -0.068% GENERIC[incl -1020(data)]
        nrf:  -440 -0.252% pca10040
        rp2: -1072 -0.217% PICO
       samd:  -368 -0.264% ADAFRUIT_ITSYBITSY_M4_EXPRESS

Performance is also improved (on bare metal at least) for the
core_import_mpy_multi.py, core_import_mpy_single.py and core_qstr.py
performance benchmarks.

Originally at adafruit#4583

Signed-off-by: Artyom Skrobov <tyomitch@gmail.com>

1 files changed, 12 insertions, 17 deletions

diff --git a/py/makeqstrdata.py b/py/makeqstrdata.py
index 403c40688..e332ab94e 100644
--- a/py/makeqstrdata.py
+++ b/py/makeqstrdata.py
@@ -317,26 +317,24 @@ def parse_input_headers(infiles):
     return qcfgs, qstrs
 
 
-def make_bytes(cfg_bytes_len, cfg_bytes_hash, qstr):
-    qbytes = bytes_cons(qstr, "utf8")
-    qlen = len(qbytes)
-    qhash = compute_hash(qbytes, cfg_bytes_hash)
+def escape_bytes(qstr, qbytes):
     if all(32 <= ord(c) <= 126 and c != "\\" and c != '"' for c in qstr):
         # qstr is all printable ASCII so render it as-is (for easier debugging)
-        qdata = qstr
+        return qstr
     else:
         # qstr contains non-printable codes so render entire thing as hex pairs
-        qdata = "".join(("\\x%02x" % b) for b in qbytes)
+        return "".join(("\\x%02x" % b) for b in qbytes)
+
+
+def make_bytes(cfg_bytes_len, cfg_bytes_hash, qstr):
+    qbytes = bytes_cons(qstr, "utf8")
+    qlen = len(qbytes)
+    qhash = compute_hash(qbytes, cfg_bytes_hash)
     if qlen >= (1 << (8 * cfg_bytes_len)):
         print("qstr is too long:", qstr)
         assert False
-    qlen_str = ("\\x%02x" * cfg_bytes_len) % tuple(
-        ((qlen >> (8 * i)) & 0xFF) for i in range(cfg_bytes_len)
-    )
-    qhash_str = ("\\x%02x" * cfg_bytes_hash) % tuple(
-        ((qhash >> (8 * i)) & 0xFF) for i in range(cfg_bytes_hash)
-    )
-    return '(const byte*)"%s%s" "%s"' % (qhash_str, qlen_str, qdata)
+    qdata = escape_bytes(qstr, qbytes)
+    return '%d, %d, "%s"' % (qhash, qlen, qdata)
 
 
 def print_qstr_data(qcfgs, qstrs):
@@ -349,10 +347,7 @@ def print_qstr_data(qcfgs, qstrs):
     print("")
 
     # add NULL qstr with no hash or data
-    print(
-        'QDEF(MP_QSTRnull, (const byte*)"%s%s" "")'
-        % ("\\x00" * cfg_bytes_hash, "\\x00" * cfg_bytes_len)
-    )
+    print('QDEF(MP_QSTRnull, 0, 0, "")')
 
     # go through each qstr and print it out
     for order, ident, qstr in sorted(qstrs.values(), key=lambda x: x[0]):