Fix libpinyin crash on ARMv7

Fix the alignment trap in get_unigram_frequency(). Fix also other
places where this same trap could happen (depending on compiler
and surrounding code).

The trap happened when the ARM GCC generated a SIMD instruction
(specifically VLDR) to load 32 bits in a single instruction, and
when the memory address was not aligned to 32 bits. VLDR traps if
the address is not aligned.

GCC generated the instruction because of the cast to uint32 from
the address. The fix is to allocate a uint32 variable in stack and
use memcpy to copy the data to that variable. This way we ensure
that appropriate instructions are generated.

**Links**

About the issue with GCC:
https://trust-in-soft.com/blog/2020/04/06/gcc-always-assumes-aligned-pointer-accesses/

How Linux does it:
https://elixir.bootlin.com/linux/v5.10.155/source/include/linux/unaligned/memmove.h#L13

ARM documentation:
https://documentation-service.arm.com/static/5f8dc043f86e16515cdbbc92?token=
    See 'A3.2.1 Unaligned data access'

1 files changed, 15 insertions, 8 deletions

diff --git a/src/storage/phrase_index.cpp b/src/storage/phrase_index.cpp
index e9e9d5d..de864c2 100644
--- a/src/storage/phrase_index.cpp
+++ b/src/storage/phrase_index.cpp
@@ -20,6 +20,7 @@
 
 #include "phrase_index.h"
 #include "pinyin_custom2.h"
+#include "unaligned_memory.h"
 
 namespace pinyin{
 
@@ -61,10 +62,12 @@ bool PhraseItem::add_pronunciation(ChewingKey * keys, guint32 delta){
     for (int i = 0; i < npron; ++i) {
         char * chewing_begin = buf_begin + offset +
             i * (phrase_length * sizeof(ChewingKey) + sizeof(guint32));
-        guint32 * freq = (guint32 *)(chewing_begin +
-                                     phrase_length * sizeof(ChewingKey));
+        
+        guint32 * pfreq = (guint32 *)(chewing_begin +
+                                      phrase_length * sizeof(ChewingKey));
+        guint32 freq = UnalignedMemory<guint32>::load(pfreq);
 
-        total_freq += *freq;
+        total_freq += freq;
 
         if (0 == pinyin_exact_compare2
             (keys, (ChewingKey *)chewing_begin, phrase_length)) {
@@ -74,8 +77,9 @@ bool PhraseItem::add_pronunciation(ChewingKey * keys, guint32 delta){
             if (delta > 0 && total_freq > total_freq + delta)
                 return false;
 
-            *freq += delta;
+            freq += delta;
             total_freq += delta;
+            UnalignedMemory<guint32>::store(freq, pfreq);
             return true;
         }
     }
@@ -117,9 +121,11 @@ void PhraseItem::increase_pronunciation_possibility(ChewingKey * keys,
     for (int i = 0; i < npron; ++i) {
         char * chewing_begin = buf_begin + offset +
             i * (phrase_length * sizeof(ChewingKey) + sizeof(guint32));
-        guint32 * freq = (guint32 *)(chewing_begin +
-                                     phrase_length * sizeof(ChewingKey));
-        total_freq += *freq;
+        
+        guint32 * pfreq = (guint32 *)(chewing_begin +
+                                      phrase_length * sizeof(ChewingKey));
+        guint32 freq = UnalignedMemory<guint32>::load(pfreq);
+        total_freq += freq;
 
         if (0 == pinyin_compare_with_tones(keys, (ChewingKey *)chewing_begin,
                                            phrase_length)) {
@@ -128,8 +134,9 @@ void PhraseItem::increase_pronunciation_possibility(ChewingKey * keys,
             if (delta > 0 && total_freq > total_freq + delta)
                 return;
 
-            *freq += delta;
+            freq += delta;
             total_freq += delta;
+            UnalignedMemory<guint32>::store(freq, pfreq);
         }
     }
 }