Restructure tables for C89 port and smaller size.

Changes the data layout of tables slightly so that string
keys are prefixed with their size, rather than the size
being inline in the table itself.

This has a few benefits:

1. inttables shrink a bit, because there is no longer a wasted
   and unused size field sitting in them.

2. This avoids the need to have a union in the table.  This is
   important for an impending C89 port of upb, since C89 has
   literally no way of statically initializing a non-first union
   member.

1 files changed, 21 insertions, 1 deletions

diff --git a/tools/dump_cinit.lua b/tools/dump_cinit.lua
index dac2498..973519b 100644
--- a/tools/dump_cinit.lua
+++ b/tools/dump_cinit.lua
@@ -47,6 +47,20 @@ function handler_types(base)
   return ret
 end
 
+function octchar(num)
+  assert(num < 8)
+  local idx = num + 1  -- 1-based index
+  return string.sub("01234567", idx, idx)
+end
+
+function c_escape(num)
+  assert(num < 256)
+  return string.format("\\%s%s%s",
+                       octchar(math.floor(num / 64)),
+                       octchar(math.floor(num / 8) % 8),
+                       octchar(num % 8));
+end
+
 -- const(f, label) -> UPB_LABEL_REPEATED, where f:label() == upb.LABEL_REPEATED
 function const(obj, name, base)
   local val = obj[name]
@@ -214,7 +228,13 @@ function Dumper:tabkey(key)
   if type(key) == "nil" then
     return "UPB_TABKEY_NONE"
   elseif type(key) == "string" then
-    return string.format('UPB_TABKEY_STR("%s")', key)
+    local len = #key
+    local len1 = c_escape(len % 256)
+    local len2 = c_escape(math.floor(len / 256) % 256)
+    local len3 = c_escape(math.floor(len / (256 * 256)) % 256)
+    local len4 = c_escape(math.floor(len / (256 * 256 * 256)) % 256)
+    return string.format('UPB_TABKEY_STR("%s", "%s", "%s", "%s", "%s")',
+                         len1, len2, len3, len4, key)
   else
     return string.format("UPB_TABKEY_NUM(%d)", key)
   end