Bug#43746: YACC return wrong query string when parse 'load data infile' sql statement

"load data" statements were written to the binlog as a mix of the original statement
and bits recreated from parse-info. This relied on implementation details and broke
with IGNORE_SPACES and versioned comments.

We now completely resynthesize the query for LOAD DATA for binlog (which among other
things normalizes them somewhat with regard to case, spaces, etc.).
We have already parsed the query properly, so we make use of that rather
than mix-and-match string literals and parsed items.
This should make us safe with regard to versioned comments, even those
spanning multiple tokens. Also no longer affected by IGNORE_SPACES.

mysql-test/r/mysqlbinlog.result:
  LOAD DATA INFILE normalized
mysql-test/suite/binlog/r/binlog_killed_simulate.result:
  LOAD DATA INFILE normalized
mysql-test/suite/binlog/r/binlog_row_mix_innodb_myisam.result:
  LOAD DATA INFILE normalized
mysql-test/suite/binlog/r/binlog_stm_blackhole.result:
  LOAD DATA INFILE normalized
mysql-test/suite/binlog/r/binlog_stm_mix_innodb_myisam.result:
  LOAD DATA INFILE normalized
mysql-test/suite/rpl/r/rpl_innodb_mixed_dml.result:
  LOAD DATA INFILE normalized
mysql-test/suite/rpl/r/rpl_loaddata.result:
  LOAD DATA INFILE normalized
mysql-test/suite/rpl/r/rpl_loaddata_fatal.result:
  LOAD DATA INFILE normalized; offsets adjusted to reflect that
mysql-test/suite/rpl/r/rpl_loaddata_map.result:
  LOAD DATA INFILE normalized
mysql-test/suite/rpl/r/rpl_loaddatalocal.result:
  test for #43746 - trying to break LOAD DATA part of parser
mysql-test/suite/rpl/r/rpl_stm_log.result:
  LOAD DATA INFILE normalized
mysql-test/suite/rpl/t/rpl_loaddatalocal.test:
  try to break the LOAD DATA part of the parser (test for #43746)
mysql-test/t/mysqlbinlog.test:
  LOAD DATA INFILE normalized; adjust offsets to reflect that
sql/log_event.cc:
  clean up Load_log_event::print_query and friends so they don't print
  excess spaces. add support for printing charset names to print_query.
sql/log_event.h:
  We already have three places where we synthesize LOAD DATA queries.
  Better use one of those!
sql/sql_lex.h:
  When binlogging LOAD DATA statements, we make up the statement to
  be logged (from the parse-info, rather than substrings of the
  original query) now. Consequently, we no longer need (string-)
  pointers into the original query.
sql/sql_load.cc:
  Completely rewrote write_execute_load_query_log_event() to synthesize the
  LOAD DATA statement wholesale, rather than piece it together from
  synthesized bits and literal excerpts from the original query. This
  will not only give us a nice, normalized statement (all uppercase,
  no excess spaces, etc.), it will also handle comments, including
  versioned comments right, which is certainly more than we can say
  about the previous incarnation.
sql/sql_yacc.yy:
  We're no longer assembling LOAD DATA statements from bodyparts of the
  original query, so some bookkeeping in the parser can go.

1 files changed, 101 insertions, 13 deletions

diff --git a/sql/sql_load.cc b/sql/sql_load.cc
index b7f33d51335..e830e29176b 100644
--- a/sql/sql_load.cc
+++ b/sql/sql_load.cc
@@ -83,10 +83,13 @@ static int read_sep_field(THD *thd, COPY_INFO &info, TABLE_LIST *table_list,
 			  String &enclosed, ulong skip_lines,
 			  bool ignore_check_option_errors);
 #ifndef EMBEDDED_LIBRARY
-static bool write_execute_load_query_log_event(THD *thd,
-					       bool duplicates, bool ignore,
-					       bool transactional_table,
-                                               int errcode);
+static bool write_execute_load_query_log_event(THD *thd, sql_exchange* ex,
+                                               const char* db_arg,
+                                               const char* table_name_arg,
+                                               enum enum_duplicates duplicates,
+                                               bool ignore,
+                                               bool transactional_table,
+                                               int errocode);
 #endif /* EMBEDDED_LIBRARY */
 
 /*
@@ -497,8 +500,10 @@ int mysql_load(THD *thd,sql_exchange *ex,TABLE_LIST *table_list,
           int errcode= query_error_code(thd, killed_status == THD::NOT_KILLED);
           
 	  if (thd->transaction.stmt.modified_non_trans_table)
-	    write_execute_load_query_log_event(thd, handle_duplicates,
-					       ignore, transactional_table,
+            write_execute_load_query_log_event(thd, ex,
+                                               tdb, table_list->table_name,
+                                               handle_duplicates, ignore,
+                                               transactional_table,
                                                errcode);
 	  else
 	  {
@@ -542,8 +547,11 @@ int mysql_load(THD *thd,sql_exchange *ex,TABLE_LIST *table_list,
       if (lf_info.wrote_create_file)
       {
         int errcode= query_error_code(thd, killed_status == THD::NOT_KILLED);
-        write_execute_load_query_log_event(thd, handle_duplicates, ignore,
-                                           transactional_table, errcode);
+        write_execute_load_query_log_event(thd, ex,
+                                           tdb, table_list->table_name,
+                                           handle_duplicates, ignore,
+                                           transactional_table,
+                                           errcode);
       }
     }
   }
@@ -564,15 +572,95 @@ err:
 #ifndef EMBEDDED_LIBRARY
 
 /* Not a very useful function; just to avoid duplication of code */
-static bool write_execute_load_query_log_event(THD *thd,
-					       bool duplicates, bool ignore,
-					       bool transactional_table,
+static bool write_execute_load_query_log_event(THD *thd, sql_exchange* ex,
+                                               const char* db_arg,
+                                               const char* table_name_arg,
+                                               enum enum_duplicates duplicates,
+                                               bool ignore,
+                                               bool transactional_table,
                                                int errcode)
 {
+  char                *load_data_query,
+                      *end,
+                      *fname_start,
+                      *fname_end,
+                      *p= NULL;
+  size_t               pl= 0;
+  List<Item>           fv;
+  Item                *item, *val;
+  String               pfield, pfields;
+  int                  n;
+
+  Load_log_event       lle(thd, ex, db_arg, table_name_arg, fv, duplicates,
+                           ignore, transactional_table);
+
+  /*
+    force in a LOCAL if there was one in the original.
+  */
+  if (thd->lex->local_file)
+    lle.set_fname_outside_temp_buf(ex->file_name, strlen(ex->file_name));
+
+  /*
+    prepare fields-list and SET if needed; print_query won't do that for us.
+  */
+  if (!thd->lex->field_list.is_empty())
+  {
+    List_iterator<Item>  li(thd->lex->field_list);
+
+    pfields.append(" (");
+    n= 0;
+
+    while ((item= li++))
+    {
+      if (n++)
+        pfields.append(", ");
+      if (item->name)
+        pfields.append(item->name);
+      else
+        item->print(&pfields, QT_ORDINARY);
+    }
+    pfields.append(")");
+  }
+
+  if (!thd->lex->update_list.is_empty())
+  {
+    List_iterator<Item> lu(thd->lex->update_list);
+    List_iterator<Item> lv(thd->lex->value_list);
+
+    pfields.append(" SET ");
+    n= 0;
+
+    while ((item= lu++))
+    {
+      val= lv++;
+      if (n++)
+        pfields.append(", ");
+      pfields.append(item->name);
+      pfields.append("=");
+      val->print(&pfields, QT_ORDINARY);
+    }
+  }
+
+  p= pfields.c_ptr_safe();
+  pl= strlen(p);
+
+  if (!(load_data_query= (char *)thd->alloc(lle.get_query_buffer_length() + 1 + pl)))
+    return TRUE;
+
+  lle.print_query(FALSE, (const char *) ex->cs?ex->cs->csname:NULL,
+                  load_data_query, &end,
+                  (char **)&fname_start, (char **)&fname_end);
+
+  strcpy(end, p);
+  end += pl;
+
+  thd->query_length= end - load_data_query;
+  thd->query= load_data_query;
+
   Execute_load_query_log_event
     e(thd, thd->query, thd->query_length,
-      (uint) ((char*)thd->lex->fname_start - (char*)thd->query),
-      (uint) ((char*)thd->lex->fname_end - (char*)thd->query),
+      (uint) ((char*)fname_start - (char*)thd->query - 1),
+      (uint) ((char*)fname_end - (char*)thd->query),
       (duplicates == DUP_REPLACE) ? LOAD_DUP_REPLACE :
       (ignore ? LOAD_DUP_IGNORE : LOAD_DUP_ERROR),
       transactional_table, FALSE, errcode);