mariadb/sql/item_xmlfunc.cc
unknown f252f9248a WL#3817: Simplify string / memory area types and make things more consistent (first part)
The following type conversions was done:

- Changed byte to uchar
- Changed gptr to uchar*
- Change my_string to char *
- Change my_size_t to size_t
- Change size_s to size_t

Removed declaration of byte, gptr, my_string, my_size_t and size_s. 

Following function parameter changes was done:
- All string functions in mysys/strings was changed to use size_t
  instead of uint for string lengths.
- All read()/write() functions changed to use size_t (including vio).
- All protocoll functions changed to use size_t instead of uint
- Functions that used a pointer to a string length was changed to use size_t*
- Changed malloc(), free() and related functions from using gptr to use void *
  as this requires fewer casts in the code and is more in line with how the
  standard functions work.
- Added extra length argument to dirname_part() to return the length of the
  created string.
- Changed (at least) following functions to take uchar* as argument:
  - db_dump()
  - my_net_write()
  - net_write_command()
  - net_store_data()
  - DBUG_DUMP()
  - decimal2bin() & bin2decimal()
- Changed my_compress() and my_uncompress() to use size_t. Changed one
  argument to my_uncompress() from a pointer to a value as we only return
  one value (makes function easier to use).
- Changed type of 'pack_data' argument to packfrm() to avoid casts.
- Changed in readfrm() and writefrom(), ha_discover and handler::discover()
  the type for argument 'frmdata' to uchar** to avoid casts.
- Changed most Field functions to use uchar* instead of char* (reduced a lot of
  casts).
- Changed field->val_xxx(xxx, new_ptr) to take const pointers.

Other changes:
- Removed a lot of not needed casts
- Added a few new cast required by other changes
- Added some cast to my_multi_malloc() arguments for safety (as string lengths
  needs to be uint, not size_t).
- Fixed all calls to hash-get-key functions to use size_t*. (Needed to be done
  explicitely as this conflict was often hided by casting the function to
  hash_get_key).
- Changed some buffers to memory regions to uchar* to avoid casts.
- Changed some string lengths from uint to size_t.
- Changed field->ptr to be uchar* instead of char*. This allowed us to
  get rid of a lot of casts.
- Some changes from true -> TRUE, false -> FALSE, unsigned char -> uchar
- Include zlib.h in some files as we needed declaration of crc32()
- Changed MY_FILE_ERROR to be (size_t) -1.
- Changed many variables to hold the result of my_read() / my_write() to be
  size_t. This was needed to properly detect errors (which are
  returned as (size_t) -1).
- Removed some very old VMS code
- Changed packfrm()/unpackfrm() to not be depending on uint size
  (portability fix)
- Removed windows specific code to restore cursor position as this
  causes slowdown on windows and we should not mix read() and pread()
  calls anyway as this is not thread safe. Updated function comment to
  reflect this. Changed function that depended on original behavior of
  my_pwrite() to itself restore the cursor position (one such case).
- Added some missing checking of return value of malloc().
- Changed definition of MOD_PAD_CHAR_TO_FULL_LENGTH to avoid 'long' overflow.
- Changed type of table_def::m_size from my_size_t to ulong to reflect that
  m_size is the number of elements in the array, not a string/memory
  length.
- Moved THD::max_row_length() to table.cc (as it's not depending on THD).
  Inlined max_row_length_blob() into this function.
- More function comments
- Fixed some compiler warnings when compiled without partitions.
- Removed setting of LEX_STRING() arguments in declaration (portability fix).
- Some trivial indentation/variable name changes.
- Some trivial code simplifications:
  - Replaced some calls to alloc_root + memcpy to use
    strmake_root()/strdup_root().
  - Changed some calls from memdup() to strmake() (Safety fix)
  - Simpler loops in client-simple.c


BitKeeper/etc/ignore:
  added libmysqld/ha_ndbcluster_cond.cc
  ---
  added debian/defs.mk debian/control
client/completion_hash.cc:
  Remove not needed casts
client/my_readline.h:
  Remove some old types
client/mysql.cc:
  Simplify types
client/mysql_upgrade.c:
  Remove some old types
  Update call to dirname_part
client/mysqladmin.cc:
  Remove some old types
client/mysqlbinlog.cc:
  Remove some old types
  Change some buffers to be uchar to avoid casts
client/mysqlcheck.c:
  Remove some old types
client/mysqldump.c:
  Remove some old types
  Remove some not needed casts
  Change some string lengths to size_t
client/mysqlimport.c:
  Remove some old types
client/mysqlshow.c:
  Remove some old types
client/mysqlslap.c:
  Remove some old types
  Remove some not needed casts
client/mysqltest.c:
  Removed some old types
  Removed some not needed casts
  Updated hash-get-key function arguments
  Updated parameters to dirname_part()
client/readline.cc:
  Removed some old types
  Removed some not needed casts
  Changed some string lengths to use size_t
client/sql_string.cc:
  Removed some old types
dbug/dbug.c:
  Removed some old types
  Changed some string lengths to use size_t
  Changed some prototypes to avoid casts
extra/comp_err.c:
  Removed some old types
extra/innochecksum.c:
  Removed some old types
extra/my_print_defaults.c:
  Removed some old types
extra/mysql_waitpid.c:
  Removed some old types
extra/perror.c:
  Removed some old types
extra/replace.c:
  Removed some old types
  Updated parameters to dirname_part()
extra/resolve_stack_dump.c:
  Removed some old types
extra/resolveip.c:
  Removed some old types
include/config-win.h:
  Removed some old types
include/decimal.h:
  Changed binary strings to be uchar* instead of char*
include/ft_global.h:
  Removed some old types
include/hash.h:
  Removed some old types
include/heap.h:
  Removed some old types
  Changed records_under_level to be 'ulong' instead of 'uint' to clarify usage of variable
include/keycache.h:
  Removed some old types
include/m_ctype.h:
  Removed some old types
  Changed some string lengths to use size_t
  Changed character length functions to return uint
  unsigned char -> uchar
include/m_string.h:
  Removed some old types
  Changed some string lengths to use size_t
include/my_alloc.h:
  Changed some string lengths to use size_t
include/my_base.h:
  Removed some old types
include/my_dbug.h:
  Removed some old types
  Changed some string lengths to use size_t
  Changed db_dump() to take uchar * as argument for memory to reduce number of casts in usage
include/my_getopt.h:
  Removed some old types
include/my_global.h:
  Removed old types:
  my_size_t -> size_t
  byte -> uchar
  gptr -> uchar *
include/my_list.h:
  Removed some old types
include/my_nosys.h:
  Removed some old types
include/my_pthread.h:
  Removed some old types
include/my_sys.h:
  Removed some old types
  Changed MY_FILE_ERROR to be in line with new definitions of my_write()/my_read()
  Changed some string lengths to use size_t
  my_malloc() / my_free() now uses void *
  Updated parameters to dirname_part() & my_uncompress()
include/my_tree.h:
  Removed some old types
include/my_trie.h:
  Removed some old types
include/my_user.h:
  Changed some string lengths to use size_t
include/my_vle.h:
  Removed some old types
include/my_xml.h:
  Removed some old types
  Changed some string lengths to use size_t
include/myisam.h:
  Removed some old types
include/myisammrg.h:
  Removed some old types
include/mysql.h:
  Removed some old types
  Changed byte streams to use uchar* instead of char*
include/mysql_com.h:
  Removed some old types
  Changed some string lengths to use size_t
  Changed some buffers to be uchar* to avoid casts
include/queues.h:
  Removed some old types
include/sql_common.h:
  Removed some old types
include/sslopt-longopts.h:
  Removed some old types
include/violite.h:
  Removed some old types
  Changed some string lengths to use size_t
libmysql/client_settings.h:
  Removed some old types
libmysql/libmysql.c:
  Removed some old types
libmysql/manager.c:
  Removed some old types
libmysqld/emb_qcache.cc:
  Removed some old types
libmysqld/emb_qcache.h:
  Removed some old types
libmysqld/lib_sql.cc:
  Removed some old types
  Removed some not needed casts
  Changed some buffers to be uchar* to avoid casts
  true -> TRUE, false -> FALSE
mysys/array.c:
  Removed some old types
mysys/charset.c:
  Changed some string lengths to use size_t
mysys/checksum.c:
  Include zlib to get definition for crc32
  Removed some old types
mysys/default.c:
  Removed some old types
  Changed some string lengths to use size_t
mysys/default_modify.c:
  Changed some string lengths to use size_t
  Removed some not needed casts
mysys/hash.c:
  Removed some old types
  Changed some string lengths to use size_t
  Note: Prototype of hash_key() has changed which may cause problems if client uses hash_init() with a cast for the hash-get-key function.
  hash_element now takes 'ulong' as the index type (cleanup)
mysys/list.c:
  Removed some old types
mysys/mf_cache.c:
  Changed some string lengths to use size_t
mysys/mf_dirname.c:
  Removed some old types
  Changed some string lengths to use size_t
  Added argument to dirname_part() to avoid calculation of length for 'to'
mysys/mf_fn_ext.c:
  Removed some old types
  Updated parameters to dirname_part()
mysys/mf_format.c:
  Removed some old types
  Changed some string lengths to use size_t
mysys/mf_getdate.c:
  Removed some old types
mysys/mf_iocache.c:
  Removed some old types
  Changed some string lengths to use size_t
  Changed calculation of 'max_length' to be done the same way in all functions
mysys/mf_iocache2.c:
  Removed some old types
  Changed some string lengths to use size_t
  Clean up comments
  Removed not needed indentation
mysys/mf_keycache.c:
  Removed some old types
mysys/mf_keycaches.c:
  Removed some old types
mysys/mf_loadpath.c:
  Removed some old types
mysys/mf_pack.c:
  Removed some old types
  Changed some string lengths to use size_t
  Removed some not needed casts
  Removed very old VMS code
  Updated parameters to dirname_part()
  Use result of dirnam_part() to remove call to strcat()
mysys/mf_path.c:
  Removed some old types
mysys/mf_radix.c:
  Removed some old types
mysys/mf_same.c:
  Removed some old types
mysys/mf_sort.c:
  Removed some old types
mysys/mf_soundex.c:
  Removed some old types
mysys/mf_strip.c:
  Removed some old types
mysys/mf_tempdir.c:
  Removed some old types
mysys/mf_unixpath.c:
  Removed some old types
mysys/mf_wfile.c:
  Removed some old types
mysys/mulalloc.c:
  Removed some old types
mysys/my_alloc.c:
  Removed some old types
  Changed some string lengths to use size_t
  Use void* as type for allocated memory area
  Removed some not needed casts
  Changed argument 'Size' to 'length' according coding guidelines
mysys/my_chsize.c:
  Changed some buffers to be uchar* to avoid casts
mysys/my_compress.c:
  More comments
  Removed some old types
  Changed string lengths to use size_t
  Changed arguments to my_uncompress() to make them easier to understand
  Changed packfrm()/unpackfrm() to not be depending on uint size (portability fix)
  Changed type of 'pack_data' argument to packfrm() to avoid casts.
mysys/my_conio.c:
  Changed some string lengths to use size_t
mysys/my_create.c:
  Removed some old types
mysys/my_div.c:
  Removed some old types
mysys/my_error.c:
  Removed some old types
mysys/my_fopen.c:
  Removed some old types
mysys/my_fstream.c:
  Removed some old types
  Changed some string lengths to use size_t
  writen -> written
mysys/my_getopt.c:
  Removed some old types
mysys/my_getwd.c:
  Removed some old types
  More comments
mysys/my_init.c:
  Removed some old types
mysys/my_largepage.c:
  Removed some old types
  Changed some string lengths to use size_t
mysys/my_lib.c:
  Removed some old types
mysys/my_lockmem.c:
  Removed some old types
mysys/my_malloc.c:
  Removed some old types
  Changed malloc(), free() and related functions to use void *
  Changed all functions to use size_t
mysys/my_memmem.c:
  Indentation cleanup
mysys/my_once.c:
  Removed some old types
  Changed malloc(), free() and related functions to use void *
mysys/my_open.c:
  Removed some old types
mysys/my_pread.c:
  Removed some old types
  Changed all functions to use size_t
  Added comment for how my_pread() / my_pwrite() are supposed to work.
  Removed windows specific code to restore cursor position as this causes slowdown on windows and we should not mix read() and pread() calls anyway as this is not thread safe.
  (If we ever would really need this, it should be enabled only with a flag argument)
mysys/my_quick.c:
  Removed some old types
  Changed all functions to use size_t
mysys/my_read.c:
  Removed some old types
  Changed all functions to use size_t
mysys/my_realloc.c:
  Removed some old types
  Use void* as type for allocated memory area
  Changed all functions to use size_t
mysys/my_static.c:
  Removed some old types
mysys/my_static.h:
  Removed some old types
mysys/my_vle.c:
  Removed some old types
mysys/my_wincond.c:
  Removed some old types
mysys/my_windac.c:
  Removed some old types
mysys/my_write.c:
  Removed some old types
  Changed all functions to use size_t
mysys/ptr_cmp.c:
  Removed some old types
  Changed all functions to use size_t
mysys/queues.c:
  Removed some old types
mysys/safemalloc.c:
  Removed some old types
  Changed malloc(), free() and related functions to use void *
  Changed all functions to use size_t
mysys/string.c:
  Removed some old types
  Changed all functions to use size_t
mysys/testhash.c:
  Removed some old types
mysys/thr_alarm.c:
  Removed some old types
mysys/thr_lock.c:
  Removed some old types
mysys/tree.c:
  Removed some old types
mysys/trie.c:
  Removed some old types
mysys/typelib.c:
  Removed some old types
plugin/daemon_example/daemon_example.cc:
  Removed some old types
regex/reginit.c:
  Removed some old types
server-tools/instance-manager/buffer.cc:
  Changed some string lengths to use size_t
  Changed buffer to be of type uchar*
server-tools/instance-manager/buffer.h:
  Changed some string lengths to use size_t
  Changed buffer to be of type uchar*
server-tools/instance-manager/commands.cc:
  Removed some old types
  Changed some string lengths to use size_t
  Changed buffer to be of type uchar*
server-tools/instance-manager/instance_map.cc:
  Removed some old types
  Changed some string lengths to use size_t
  Changed buffer to be of type uchar*
server-tools/instance-manager/instance_options.cc:
  Changed buffer to be of type uchar*
  Replaced alloc_root + strcpy() with strdup_root()
server-tools/instance-manager/mysql_connection.cc:
  Changed buffer to be of type uchar*
server-tools/instance-manager/options.cc:
  Removed some old types
server-tools/instance-manager/parse.cc:
  Changed some string lengths to use size_t
server-tools/instance-manager/parse.h:
  Removed some old types
  Changed some string lengths to use size_t
server-tools/instance-manager/protocol.cc:
  Changed some buffers to be uchar* to avoid casts
  Changed some string lengths to use size_t
server-tools/instance-manager/protocol.h:
  Changed some string lengths to use size_t
server-tools/instance-manager/user_map.cc:
  Removed some old types
  Changed some string lengths to use size_t
sql/derror.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Changed some string lengths to use size_t
sql/discover.cc:
  Changed in readfrm() and writefrom() the type for argument 'frmdata' to uchar** to avoid casts
  Changed some string lengths to use size_t
  Changed some buffers to be uchar* to avoid casts
sql/event_data_objects.cc:
  Removed some old types
  Added missing casts for alloc() and sprintf()
sql/event_db_repository.cc:
  Changed some buffers to be uchar* to avoid casts
  Added missing casts for sprintf()
sql/event_queue.cc:
  Removed some old types
sql/field.cc:
  Removed some old types
  Changed memory buffers to be uchar*
  Changed some string lengths to use size_t
  Removed a lot of casts
  Safety fix in Field_blob::val_decimal() to not access zero pointer
sql/field.h:
  Removed some old types
  Changed memory buffers to be uchar* (except of store() as this would have caused too many other changes). 
  Changed some string lengths to use size_t
  Removed some not needed casts
  Changed val_xxx(xxx, new_ptr) to take const pointers
sql/field_conv.cc:
  Removed some old types
  Added casts required because memory area pointers are now uchar*
sql/filesort.cc:
  Initalize variable that was used unitialized in error conditions
sql/gen_lex_hash.cc:
  Removed some old types
  Changed memory buffers to be uchar*
  Changed some string lengths to use size_t
  Removed a lot of casts
  Safety fix in Field_blob::val_decimal() to not access zero pointer
sql/gstream.h:
  Added required cast
sql/ha_ndbcluster.cc:
  Removed some old types
  Updated hash-get-key function arguments
  Changed some buffers to be uchar* to avoid casts
  Added required casts
  Removed some not needed casts
sql/ha_ndbcluster.h:
  Removed some old types
sql/ha_ndbcluster_binlog.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Replaced sql_alloc() + memcpy() + set end 0 with sql_strmake()
  Changed some string lengths to use size_t
  Added missing casts for alloc() and sprintf()
sql/ha_ndbcluster_binlog.h:
  Removed some old types
sql/ha_ndbcluster_cond.cc:
  Removed some old types
  Removed some not needed casts
sql/ha_ndbcluster_cond.h:
  Removed some old types
sql/ha_partition.cc:
  Removed some old types
  Changed prototype for change_partition() to avoid casts
sql/ha_partition.h:
  Removed some old types
sql/handler.cc:
  Removed some old types
  Changed some string lengths to use size_t
sql/handler.h:
  Removed some old types
  Changed some string lengths to use size_t
  Changed type for 'frmblob' parameter for discover() and ha_discover() to get fewer casts
sql/hash_filo.h:
  Removed some old types
  Changed all functions to use size_t
sql/hostname.cc:
  Removed some old types
sql/item.cc:
  Removed some old types
  Changed some string lengths to use size_t
  Use strmake() instead of memdup() to create a null terminated string.
  Updated calls to new Field()
sql/item.h:
  Removed some old types
  Changed malloc(), free() and related functions to use void *
  Changed some buffers to be uchar* to avoid casts
sql/item_cmpfunc.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
sql/item_cmpfunc.h:
  Removed some old types
sql/item_create.cc:
  Removed some old types
sql/item_func.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
  Added test for failing alloc() in init_result_field()
  Remove old confusing comment
  Fixed compiler warning
sql/item_func.h:
  Removed some old types
sql/item_row.cc:
  Removed some old types
sql/item_row.h:
  Removed some old types
sql/item_strfunc.cc:
  Include zlib (needed becasue we call crc32)
  Removed some old types
sql/item_strfunc.h:
  Removed some old types
  Changed some types to match new function prototypes
sql/item_subselect.cc:
  Removed some old types
sql/item_subselect.h:
  Removed some old types
sql/item_sum.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
sql/item_sum.h:
  Removed some old types
sql/item_timefunc.cc:
  Removed some old types
  Changed some string lengths to use size_t
sql/item_timefunc.h:
  Removed some old types
sql/item_xmlfunc.cc:
  Changed some string lengths to use size_t
sql/item_xmlfunc.h:
  Removed some old types
sql/key.cc:
  Removed some old types
  Removed some not needed casts
sql/lock.cc:
  Removed some old types
  Added some cast to my_multi_malloc() arguments for safety
sql/log.cc:
  Removed some old types
  Changed some string lengths to use size_t
  Changed some buffers to be uchar* to avoid casts
  Changed usage of pwrite() to not assume it holds the cursor position for the file
  Made usage of my_read() safer
sql/log_event.cc:
  Removed some old types
  Added checking of return value of malloc() in pack_info()
  Changed some buffers to be uchar* to avoid casts
  Removed some 'const' to avoid casts
  Added missing casts for alloc() and sprintf()
  Added required casts
  Removed some not needed casts
  Added some cast to my_multi_malloc() arguments for safety
sql/log_event.h:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
sql/log_event_old.cc:
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
sql/log_event_old.h:
  Changed some buffers to be uchar* to avoid casts
sql/mf_iocache.cc:
  Removed some old types
sql/my_decimal.cc:
  Changed memory area to use uchar*
sql/my_decimal.h:
  Changed memory area to use uchar*
sql/mysql_priv.h:
  Removed some old types
  Changed malloc(), free() and related functions to use void *
  Changed some string lengths to use size_t
  Changed definition of MOD_PAD_CHAR_TO_FULL_LENGTH to avoid long overflow
  Changed some buffers to be uchar* to avoid casts
sql/mysqld.cc:
  Removed some old types
sql/net_serv.cc:
  Removed some old types
  Changed some string lengths to use size_t
  Changed some buffers to be uchar* to avoid casts
  Ensure that vio_read()/vio_write() return values are stored in a size_t variable
  Removed some not needed casts
sql/opt_range.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
sql/opt_range.h:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
sql/opt_sum.cc:
  Removed some old types
  Removed some not needed casts
sql/parse_file.cc:
  Removed some old types
  Changed some string lengths to use size_t
  Changed alloc_root + memcpy + set end 0 -> strmake_root()
sql/parse_file.h:
  Removed some old types
sql/partition_info.cc:
  Removed some old types
  Added missing casts for alloc()
  Changed some buffers to be uchar* to avoid casts
sql/partition_info.h:
  Changed some buffers to be uchar* to avoid casts
sql/protocol.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
sql/protocol.h:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Changed some string lengths to use size_t
sql/records.cc:
  Removed some old types
sql/repl_failsafe.cc:
  Removed some old types
  Changed some string lengths to use size_t
  Added required casts
sql/rpl_filter.cc:
  Removed some old types
  Updated hash-get-key function arguments
  Changed some string lengths to use size_t
sql/rpl_filter.h:
  Changed some string lengths to use size_t
sql/rpl_injector.h:
  Removed some old types
sql/rpl_record.cc:
  Removed some old types
  Removed some not needed casts
  Changed some buffers to be uchar* to avoid casts
sql/rpl_record.h:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
sql/rpl_record_old.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
sql/rpl_record_old.h:
  Removed some old types
  Changed some buffers to be uchar* to avoid cast
sql/rpl_rli.cc:
  Removed some old types
sql/rpl_tblmap.cc:
  Removed some old types
sql/rpl_tblmap.h:
  Removed some old types
sql/rpl_utility.cc:
  Removed some old types
sql/rpl_utility.h:
  Removed some old types
  Changed type of m_size from my_size_t to ulong to reflect that m_size is the number of elements in the array, not a string/memory length
sql/set_var.cc:
  Removed some old types
  Updated parameters to dirname_part()
sql/set_var.h:
  Removed some old types
sql/slave.cc:
  Removed some old types
  Changed some string lengths to use size_t
sql/slave.h:
  Removed some old types
sql/sp.cc:
  Removed some old types
  Added missing casts for printf()
sql/sp.h:
  Removed some old types
  Updated hash-get-key function arguments
sql/sp_cache.cc:
  Removed some old types
  Added missing casts for printf()
  Updated hash-get-key function arguments
sql/sp_head.cc:
  Removed some old types
  Added missing casts for alloc() and printf()
  Added required casts
  Updated hash-get-key function arguments
sql/sp_head.h:
  Removed some old types
sql/sp_pcontext.cc:
  Removed some old types
sql/sp_pcontext.h:
  Removed some old types
sql/sql_acl.cc:
  Removed some old types
  Changed some string lengths to use size_t
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
  Added required casts
sql/sql_analyse.cc:
  Changed some buffers to be uchar* to avoid casts
sql/sql_analyse.h:
  Changed some buffers to be uchar* to avoid casts
sql/sql_array.h:
  Removed some old types
sql/sql_base.cc:
  Removed some old types
  Updated hash-get-key function arguments
sql/sql_binlog.cc:
  Removed some old types
  Added missing casts for printf()
sql/sql_cache.cc:
  Removed some old types
  Updated hash-get-key function arguments
  Removed some not needed casts
  Changed some string lengths to use size_t
sql/sql_cache.h:
  Removed some old types
  Removed reference to not existing function cache_key()
  Updated hash-get-key function arguments
sql/sql_class.cc:
  Removed some old types
  Updated hash-get-key function arguments
  Added missing casts for alloc()
  Updated hash-get-key function arguments
  Moved THD::max_row_length() to table.cc (as it's not depending on THD)
  Removed some not needed casts
sql/sql_class.h:
  Removed some old types
  Changed malloc(), free() and related functions to use void *
  Removed some not needed casts
  Changed some string lengths to use size_t
  Moved max_row_length and max_row_length_blob() to table.cc, as they are not depending on THD
sql/sql_connect.cc:
  Removed some old types
  Added required casts
sql/sql_db.cc:
  Removed some old types
  Removed some not needed casts
  Added some cast to my_multi_malloc() arguments for safety
  Added missing casts for alloc()
sql/sql_delete.cc:
  Removed some old types
sql/sql_handler.cc:
  Removed some old types
  Updated hash-get-key function arguments
  Added some cast to my_multi_malloc() arguments for safety
sql/sql_help.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
sql/sql_insert.cc:
  Removed some old types
  Added missing casts for alloc() and printf()
sql/sql_lex.cc:
  Removed some old types
sql/sql_lex.h:
  Removed some old types
  Removed some not needed casts
sql/sql_list.h:
  Removed some old types
  Removed some not needed casts
sql/sql_load.cc:
  Removed some old types
  Removed compiler warning
sql/sql_manager.cc:
  Removed some old types
sql/sql_map.cc:
  Removed some old types
sql/sql_map.h:
  Removed some old types
sql/sql_olap.cc:
  Removed some old types
sql/sql_parse.cc:
  Removed some old types
  Trivial move of code lines to make things more readable
  Changed some string lengths to use size_t
  Added missing casts for alloc()
sql/sql_partition.cc:
  Removed some old types
  Removed compiler warnings about not used functions
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
sql/sql_partition.h:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
sql/sql_plugin.cc:
  Removed some old types
  Added missing casts for alloc()
  Updated hash-get-key function arguments
sql/sql_prepare.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Added missing casts for alloc() and printf()
sql-common/client.c:
  Removed some old types
  Changed some memory areas to use uchar*
sql-common/my_user.c:
  Changed some string lengths to use size_t
sql-common/pack.c:
  Changed some buffers to be uchar* to avoid casts
sql/sql_repl.cc:
  Added required casts
  Changed some buffers to be uchar* to avoid casts
  Changed some string lengths to use size_t
sql/sql_select.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Removed some old types
sql/sql_select.h:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
sql/sql_servers.cc:
  Removed some old types
  Updated hash-get-key function arguments
sql/sql_show.cc:
  Removed some old types
  Added missing casts for alloc()
  Removed some not needed casts
sql/sql_string.cc:
  Removed some old types
  Added required casts
sql/sql_table.cc:
  Removed some old types
  Removed compiler warning about not used variable
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
sql/sql_test.cc:
  Removed some old types
sql/sql_trigger.cc:
  Removed some old types
  Added missing casts for alloc()
sql/sql_udf.cc:
  Removed some old types
  Updated hash-get-key function arguments
sql/sql_union.cc:
  Removed some old types
sql/sql_update.cc:
  Removed some old types
  Removed some not needed casts
sql/sql_view.cc:
  Removed some old types
sql/sql_yacc.yy:
  Removed some old types
  Changed some string lengths to use size_t
  Added missing casts for alloc()
sql/stacktrace.c:
  Removed some old types
sql/stacktrace.h:
  Removed some old types
sql/structs.h:
  Removed some old types
sql/table.cc:
  Removed some old types
  Updated hash-get-key function arguments
  Changed some buffers to be uchar* to avoid casts
  Removed setting of LEX_STRING() arguments in declaration
  Added required casts
  More function comments
  Moved max_row_length() here from sql_class.cc/sql_class.h
sql/table.h:
  Removed some old types
  Changed some string lengths to use size_t
sql/thr_malloc.cc:
  Use void* as type for allocated memory area
  Changed all functions to use size_t
sql/tzfile.h:
  Changed some buffers to be uchar* to avoid casts
sql/tztime.cc:
  Changed some buffers to be uchar* to avoid casts
  Updated hash-get-key function arguments
  Added missing casts for alloc()
  Removed some not needed casts
sql/uniques.cc:
  Removed some old types
  Removed some not needed casts
sql/unireg.cc:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
  Removed some not needed casts
  Added missing casts for alloc()
storage/archive/archive_reader.c:
  Removed some old types
storage/archive/azio.c:
  Removed some old types
  Removed some not needed casts
storage/archive/ha_archive.cc:
  Removed some old types
  Changed type for 'frmblob' in archive_discover() to match handler
  Updated hash-get-key function arguments
  Removed some not needed casts
storage/archive/ha_archive.h:
  Removed some old types
storage/blackhole/ha_blackhole.cc:
  Removed some old types
storage/blackhole/ha_blackhole.h:
  Removed some old types
storage/csv/ha_tina.cc:
  Removed some old types
  Updated hash-get-key function arguments
  Changed some buffers to be uchar* to avoid casts
storage/csv/ha_tina.h:
  Removed some old types
  Removed some not needed casts
storage/csv/transparent_file.cc:
  Removed some old types
  Changed type of 'bytes_read' to be able to detect read errors
  Fixed indentation
storage/csv/transparent_file.h:
  Removed some old types
storage/example/ha_example.cc:
  Removed some old types
  Updated hash-get-key function arguments
storage/example/ha_example.h:
  Removed some old types
storage/federated/ha_federated.cc:
  Removed some old types
  Updated hash-get-key function arguments
  Removed some not needed casts
storage/federated/ha_federated.h:
  Removed some old types
storage/heap/_check.c:
  Changed some buffers to be uchar* to avoid casts
storage/heap/_rectest.c:
  Removed some old types
storage/heap/ha_heap.cc:
  Removed some old types
storage/heap/ha_heap.h:
  Removed some old types
storage/heap/heapdef.h:
  Removed some old types
storage/heap/hp_block.c:
  Removed some old types
  Changed some string lengths to use size_t
storage/heap/hp_clear.c:
  Removed some old types
storage/heap/hp_close.c:
  Removed some old types
storage/heap/hp_create.c:
  Removed some old types
storage/heap/hp_delete.c:
  Removed some old types
storage/heap/hp_hash.c:
  Removed some old types
storage/heap/hp_info.c:
  Removed some old types
storage/heap/hp_open.c:
  Removed some old types
storage/heap/hp_rfirst.c:
  Removed some old types
storage/heap/hp_rkey.c:
  Removed some old types
storage/heap/hp_rlast.c:
  Removed some old types
storage/heap/hp_rnext.c:
  Removed some old types
storage/heap/hp_rprev.c:
  Removed some old types
storage/heap/hp_rrnd.c:
  Removed some old types
storage/heap/hp_rsame.c:
  Removed some old types
storage/heap/hp_scan.c:
  Removed some old types
storage/heap/hp_test1.c:
  Removed some old types
storage/heap/hp_test2.c:
  Removed some old types
storage/heap/hp_update.c:
  Removed some old types
storage/heap/hp_write.c:
  Removed some old types
  Changed some string lengths to use size_t
storage/innobase/handler/ha_innodb.cc:
  Removed some old types
  Updated hash-get-key function arguments
  Added missing casts for alloc() and printf()
  Removed some not needed casts
storage/innobase/handler/ha_innodb.h:
  Removed some old types
storage/myisam/ft_boolean_search.c:
  Removed some old types
storage/myisam/ft_nlq_search.c:
  Removed some old types
storage/myisam/ft_parser.c:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
storage/myisam/ft_static.c:
  Removed some old types
storage/myisam/ft_stopwords.c:
  Removed some old types
storage/myisam/ft_update.c:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
storage/myisam/ftdefs.h:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
storage/myisam/fulltext.h:
  Removed some old types
storage/myisam/ha_myisam.cc:
  Removed some old types
storage/myisam/ha_myisam.h:
  Removed some old types
storage/myisam/mi_cache.c:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
storage/myisam/mi_check.c:
  Removed some old types
storage/myisam/mi_checksum.c:
  Removed some old types
storage/myisam/mi_close.c:
  Removed some old types
storage/myisam/mi_create.c:
  Removed some old types
storage/myisam/mi_delete.c:
  Removed some old types
storage/myisam/mi_delete_all.c:
  Removed some old types
storage/myisam/mi_dynrec.c:
  Removed some old types
storage/myisam/mi_extra.c:
  Removed some old types
storage/myisam/mi_key.c:
  Removed some old types
storage/myisam/mi_locking.c:
  Removed some old types
storage/myisam/mi_log.c:
  Removed some old types
storage/myisam/mi_open.c:
  Removed some old types
  Removed some not needed casts
  Check argument of my_write()/my_pwrite() in functions returning int
  Added casting of string lengths to size_t
storage/myisam/mi_packrec.c:
  Removed some old types
  Changed some buffers to be uchar* to avoid casts
storage/myisam/mi_page.c:
  Removed some old types
storage/myisam/mi_preload.c:
  Removed some old types
storage/myisam/mi_range.c:
  Removed some old types
storage/myisam/mi_rfirst.c:
  Removed some old types
storage/myisam/mi_rkey.c:
  Removed some old types
storage/myisam/mi_rlast.c:
  Removed some old types
storage/myisam/mi_rnext.c:
  Removed some old types
storage/myisam/mi_rnext_same.c:
  Removed some old types
storage/myisam/mi_rprev.c:
  Removed some old types
storage/myisam/mi_rrnd.c:
  Removed some old types
storage/myisam/mi_rsame.c:
  Removed some old types
storage/myisam/mi_rsamepos.c:
  Removed some old types
storage/myisam/mi_scan.c:
  Removed some old types
storage/myisam/mi_search.c:
  Removed some old types
storage/myisam/mi_static.c:
  Removed some old types
storage/myisam/mi_statrec.c:
  Removed some old types
storage/myisam/mi_test1.c:
  Removed some old types
storage/myisam/mi_test2.c:
  Removed some old types
storage/myisam/mi_test3.c:
  Removed some old types
storage/myisam/mi_unique.c:
  Removed some old types
storage/myisam/mi_update.c:
  Removed some old types
storage/myisam/mi_write.c:
  Removed some old types
storage/myisam/myisam_ftdump.c:
  Removed some old types
storage/myisam/myisamchk.c:
  Removed some old types
storage/myisam/myisamdef.h:
  Removed some old types
storage/myisam/myisamlog.c:
  Removed some old types
  Indentation fix
storage/myisam/myisampack.c:
  Removed some old types
storage/myisam/rt_index.c:
  Removed some old types
storage/myisam/rt_split.c:
  Removed some old types
storage/myisam/sort.c:
  Removed some old types
storage/myisam/sp_defs.h:
  Removed some old types
storage/myisam/sp_key.c:
  Removed some old types
storage/myisammrg/ha_myisammrg.cc:
  Removed some old types
storage/myisammrg/ha_myisammrg.h:
  Removed some old types
storage/myisammrg/myrg_close.c:
  Removed some old types
storage/myisammrg/myrg_def.h:
  Removed some old types
storage/myisammrg/myrg_delete.c:
  Removed some old types
storage/myisammrg/myrg_open.c:
  Removed some old types
  Updated parameters to dirname_part()
storage/myisammrg/myrg_queue.c:
  Removed some old types
storage/myisammrg/myrg_rfirst.c:
  Removed some old types
storage/myisammrg/myrg_rkey.c:
  Removed some old types
storage/myisammrg/myrg_rlast.c:
  Removed some old types
storage/myisammrg/myrg_rnext.c:
  Removed some old types
storage/myisammrg/myrg_rnext_same.c:
  Removed some old types
storage/myisammrg/myrg_rprev.c:
  Removed some old types
storage/myisammrg/myrg_rrnd.c:
  Removed some old types
storage/myisammrg/myrg_rsame.c:
  Removed some old types
storage/myisammrg/myrg_update.c:
  Removed some old types
storage/myisammrg/myrg_write.c:
  Removed some old types
storage/ndb/include/util/ndb_opts.h:
  Removed some old types
storage/ndb/src/cw/cpcd/main.cpp:
  Removed some old types
storage/ndb/src/kernel/vm/Configuration.cpp:
  Removed some old types
storage/ndb/src/mgmclient/main.cpp:
  Removed some old types
storage/ndb/src/mgmsrv/InitConfigFileParser.cpp:
  Removed some old types
  Removed old disabled code
storage/ndb/src/mgmsrv/main.cpp:
  Removed some old types
storage/ndb/src/ndbapi/NdbBlob.cpp:
  Removed some old types
storage/ndb/src/ndbapi/NdbOperationDefine.cpp:
  Removed not used variable
storage/ndb/src/ndbapi/NdbOperationInt.cpp:
  Added required casts
storage/ndb/src/ndbapi/NdbScanOperation.cpp:
  Added required casts
storage/ndb/tools/delete_all.cpp:
  Removed some old types
storage/ndb/tools/desc.cpp:
  Removed some old types
storage/ndb/tools/drop_index.cpp:
  Removed some old types
storage/ndb/tools/drop_tab.cpp:
  Removed some old types
storage/ndb/tools/listTables.cpp:
  Removed some old types
storage/ndb/tools/ndb_config.cpp:
  Removed some old types
storage/ndb/tools/restore/consumer_restore.cpp:
  Changed some buffers to be uchar* to avoid casts with new defintion of packfrm()
storage/ndb/tools/restore/restore_main.cpp:
  Removed some old types
storage/ndb/tools/select_all.cpp:
  Removed some old types
storage/ndb/tools/select_count.cpp:
  Removed some old types
storage/ndb/tools/waiter.cpp:
  Removed some old types
strings/bchange.c:
  Changed function to use uchar * and size_t
strings/bcmp.c:
  Changed function to use uchar * and size_t
strings/bmove512.c:
  Changed function to use uchar * and size_t
strings/bmove_upp.c:
  Changed function to use uchar * and size_t
strings/ctype-big5.c:
  Changed functions to use size_t
  Changed character length functions to return uint
strings/ctype-bin.c:
  Changed functions to use size_t
strings/ctype-cp932.c:
  Changed functions to use size_t
  Changed character length functions to return uint
strings/ctype-czech.c:
  Fixed indentation
  Changed functions to use size_t
strings/ctype-euc_kr.c:
  Changed functions to use size_t
  Changed character length functions to return uint
strings/ctype-eucjpms.c:
  Changed functions to use size_t
  Changed character length functions to return uint
  unsigned char -> uchar
strings/ctype-gb2312.c:
  Changed functions to use size_t
  Changed character length functions to return uint
strings/ctype-gbk.c:
  Changed functions to use size_t
  Changed character length functions to return uint
strings/ctype-latin1.c:
  Changed functions to use size_t
  Changed character length functions to return uint
  unsigned char -> uchar
strings/ctype-mb.c:
  Changed functions to use size_t
  Changed character length functions to return uint
strings/ctype-simple.c:
  Changed functions to use size_t
  Simpler loops for caseup/casedown
  unsigned int -> uint
  unsigned char -> uchar
strings/ctype-sjis.c:
  Changed functions to use size_t
  Changed character length functions to return uint
strings/ctype-tis620.c:
  Changed functions to use size_t
  Changed character length functions to return uint
  unsigned char -> uchar
strings/ctype-uca.c:
  Changed functions to use size_t
  unsigned char -> uchar
strings/ctype-ucs2.c:
  Moved inclusion of stdarg.h to other includes
  usigned char -> uchar
  Changed functions to use size_t
  Changed character length functions to return uint
strings/ctype-ujis.c:
  Changed functions to use size_t
  Changed character length functions to return uint
  unsigned char -> uchar
strings/ctype-utf8.c:
  Changed functions to use size_t
  unsigned char -> uchar
  Indentation fixes
strings/ctype-win1250ch.c:
  Indentation fixes
  Changed functions to use size_t
strings/ctype.c:
  Changed functions to use size_t
strings/decimal.c:
  Changed type for memory argument to uchar *
strings/do_ctype.c:
  Indentation fixes
strings/my_strtoll10.c:
  unsigned char -> uchar
strings/my_vsnprintf.c:
  Changed functions to use size_t
strings/r_strinstr.c:
  Removed some old types
  Changed functions to use size_t
strings/str_test.c:
  Removed some old types
strings/strappend.c:
  Changed functions to use size_t
strings/strcont.c:
  Removed some old types
strings/strfill.c:
  Removed some old types
strings/strinstr.c:
  Changed functions to use size_t
strings/strlen.c:
  Changed functions to use size_t
strings/strmake.c:
  Changed functions to use size_t
strings/strnlen.c:
  Changed functions to use size_t
strings/strnmov.c:
  Changed functions to use size_t
strings/strto.c:
  unsigned char -> uchar
strings/strtod.c:
  Changed functions to use size_t
strings/strxnmov.c:
  Changed functions to use size_t
strings/xml.c:
  Changed functions to use size_t
  Indentation fixes
tests/mysql_client_test.c:
  Removed some old types
tests/thread_test.c:
  Removed some old types
vio/test-ssl.c:
  Removed some old types
vio/test-sslclient.c:
  Removed some old types
vio/test-sslserver.c:
  Removed some old types
vio/vio.c:
  Removed some old types
vio/vio_priv.h:
  Removed some old types
  Changed vio_read()/vio_write() to work with size_t
vio/viosocket.c:
  Changed vio_read()/vio_write() to work with size_t
  Indentation fixes
vio/viossl.c:
  Changed vio_read()/vio_write() to work with size_t
  Indentation fixes
vio/viosslfactories.c:
  Removed some old types
vio/viotest-ssl.c:
  Removed some old types
win/README:
  More explanations
2007-05-10 12:59:39 +03:00

2779 lines
70 KiB
C++
Raw Blame History

/* Copyright (C) 2005-2006 MySQL AB
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; version 2 of the License.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */
#ifdef __GNUC__
#pragma implementation
#endif
#include "mysql_priv.h"
#include "my_xml.h"
/*
TODO: future development directions:
1. add real constants for XPATH_NODESET_CMP and XPATH_NODESET
into enum Type in item.h.
2. add nodeset_to_nodeset_comparator
3. add lacking functions:
- name()
- lang()
- string()
- id()
- translate()
- local-name()
- starts-with()
- namespace-uri()
- substring-after()
- normalize-space()
- substring-before()
4. add lacking axis:
- following-sibling
- following,
- preceding-sibling
- preceding
*/
/* Structure to store a parsed XML tree */
typedef struct my_xml_node_st
{
uint level; /* level in XML tree, 0 means root node */
enum my_xml_node_type type; /* node type: node, or attribute, or text */
uint parent; /* link to the parent */
const char *beg; /* beginning of the name or text */
const char *end; /* end of the name or text */
const char *tagend; /* where this tag ends */
} MY_XML_NODE;
/* Lexical analizer token */
typedef struct my_xpath_lex_st
{
int term; /* token type, see MY_XPATH_LEX_XXXXX below */
const char *beg; /* beginnign of the token */
const char *end; /* end of the token */
} MY_XPATH_LEX;
/* Structure to store nodesets */
typedef struct my_xpath_flt_st
{
uint num; /* absolute position in MY_XML_NODE array */
uint pos; /* relative position in context */
uint size; /* context size */
} MY_XPATH_FLT;
/* XPath function creator */
typedef struct my_xpath_function_names_st
{
const char *name; /* function name */
size_t length; /* function name length */
size_t minargs; /* min number of arguments */
size_t maxargs; /* max number of arguments */
Item *(*create)(struct my_xpath_st *xpath, Item **args, uint nargs);
} MY_XPATH_FUNC;
/* XPath query parser */
typedef struct my_xpath_st
{
int debug;
MY_XPATH_LEX query; /* Whole query */
MY_XPATH_LEX lasttok; /* last scanned token */
MY_XPATH_LEX prevtok; /* previous scanned token */
int axis; /* last scanned axis */
int extra; /* last scanned "extra", context dependent */
MY_XPATH_FUNC *func; /* last scanned function creator */
Item *item; /* current expression */
Item *context; /* last scanned context */
Item *rootelement; /* The root element */
String *context_cache; /* last context provider */
String *pxml; /* Parsed XML, an array of MY_XML_NODE */
CHARSET_INFO *cs; /* character set/collation string comparison */
int error;
} MY_XPATH;
/* Dynamic array of MY_XPATH_FLT */
class XPathFilter :public String
{
public:
XPathFilter() :String() {}
inline bool append_element(MY_XPATH_FLT *flt)
{
String *str= this;
return str->append((const char*)flt, (uint32) sizeof(MY_XPATH_FLT));
}
inline bool append_element(uint32 num, uint32 pos)
{
MY_XPATH_FLT add;
add.num= num;
add.pos= pos;
add.size= 0;
return append_element(&add);
}
inline bool append_element(uint32 num, uint32 pos, uint32 size)
{
MY_XPATH_FLT add;
add.num= num;
add.pos= pos;
add.size= size;
return append_element(&add);
}
inline MY_XPATH_FLT *element(uint i)
{
return (MY_XPATH_FLT*) (ptr() + i * sizeof(MY_XPATH_FLT));
}
inline uint32 numelements()
{
return length() / sizeof(MY_XPATH_FLT);
}
};
/*
Common features of the functions returning a node set.
*/
class Item_nodeset_func :public Item_str_func
{
protected:
String tmp_value, tmp2_value;
MY_XPATH_FLT *fltbeg, *fltend;
MY_XML_NODE *nodebeg, *nodeend;
uint numnodes;
public:
String *pxml;
String context_cache;
Item_nodeset_func(String *pxml_arg) :Item_str_func(), pxml(pxml_arg) {}
Item_nodeset_func(Item *a, String *pxml_arg)
:Item_str_func(a), pxml(pxml_arg) {}
Item_nodeset_func(Item *a, Item *b, String *pxml_arg)
:Item_str_func(a, b), pxml(pxml_arg) {}
Item_nodeset_func(Item *a, Item *b, Item *c, String *pxml_arg)
:Item_str_func(a,b,c), pxml(pxml_arg) {}
void prepare_nodes()
{
nodebeg= (MY_XML_NODE*) pxml->ptr();
nodeend= (MY_XML_NODE*) (pxml->ptr() + pxml->length());
numnodes= nodeend - nodebeg;
}
void prepare(String *nodeset)
{
prepare_nodes();
String *res= args[0]->val_nodeset(&tmp_value);
fltbeg= (MY_XPATH_FLT*) res->ptr();
fltend= (MY_XPATH_FLT*) (res->ptr() + res->length());
nodeset->length(0);
}
enum Type type() const { return XPATH_NODESET; }
String *val_str(String *str)
{
prepare_nodes();
String *res= val_nodeset(&tmp2_value);
fltbeg= (MY_XPATH_FLT*) res->ptr();
fltend= (MY_XPATH_FLT*) (res->ptr() + res->length());
String active;
active.alloc(numnodes);
bzero((char*) active.ptr(), numnodes);
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
MY_XML_NODE *node;
uint j;
for (j=0, node= nodebeg ; j < numnodes; j++, node++)
{
if (node->type == MY_XML_NODE_TEXT &&
node->parent == flt->num)
active[j]= 1;
}
}
str->length(0);
str->set_charset(collation.collation);
for (uint i=0 ; i < numnodes; i++)
{
if(active[i])
{
if (str->length())
str->append(" ", 1, &my_charset_latin1);
str->append(nodebeg[i].beg, nodebeg[i].end - nodebeg[i].beg);
}
}
return str;
}
enum Item_result result_type () const { return STRING_RESULT; }
void fix_length_and_dec()
{
max_length= MAX_BLOB_WIDTH;
collation.collation= pxml->charset();
}
const char *func_name() const { return "nodeset"; }
};
/* Returns an XML root */
class Item_nodeset_func_rootelement :public Item_nodeset_func
{
public:
Item_nodeset_func_rootelement(String *pxml): Item_nodeset_func(pxml) {}
const char *func_name() const { return "xpath_rootelement"; }
String *val_nodeset(String *nodeset);
};
/* Returns a Union of two node sets */
class Item_nodeset_func_union :public Item_nodeset_func
{
public:
Item_nodeset_func_union(Item *a, Item *b, String *pxml)
:Item_nodeset_func(a, b, pxml) {}
const char *func_name() const { return "xpath_union"; }
String *val_nodeset(String *nodeset);
};
/* Makes one step towards the given axis */
class Item_nodeset_func_axisbyname :public Item_nodeset_func
{
const char *node_name;
uint node_namelen;
public:
Item_nodeset_func_axisbyname(Item *a, const char *n_arg, uint l_arg,
String *pxml):
Item_nodeset_func(a, pxml), node_name(n_arg), node_namelen(l_arg) { }
const char *func_name() const { return "xpath_axisbyname"; }
bool validname(MY_XML_NODE *n)
{
if (node_name[0] == '*')
return 1;
return (node_namelen == (uint) (n->end - n->beg)) &&
!memcmp(node_name, n->beg, node_namelen);
}
};
/* Returns self */
class Item_nodeset_func_selfbyname: public Item_nodeset_func_axisbyname
{
public:
Item_nodeset_func_selfbyname(Item *a, const char *n_arg, uint l_arg,
String *pxml):
Item_nodeset_func_axisbyname(a, n_arg, l_arg, pxml) {}
const char *func_name() const { return "xpath_selfbyname"; }
String *val_nodeset(String *nodeset);
};
/* Returns children */
class Item_nodeset_func_childbyname: public Item_nodeset_func_axisbyname
{
public:
Item_nodeset_func_childbyname(Item *a, const char *n_arg, uint l_arg,
String *pxml):
Item_nodeset_func_axisbyname(a, n_arg, l_arg, pxml) {}
const char *func_name() const { return "xpath_childbyname"; }
String *val_nodeset(String *nodeset);
};
/* Returns descendants */
class Item_nodeset_func_descendantbyname: public Item_nodeset_func_axisbyname
{
bool need_self;
public:
Item_nodeset_func_descendantbyname(Item *a, const char *n_arg, uint l_arg,
String *pxml, bool need_self_arg):
Item_nodeset_func_axisbyname(a, n_arg, l_arg, pxml),
need_self(need_self_arg) {}
const char *func_name() const { return "xpath_descendantbyname"; }
String *val_nodeset(String *nodeset);
};
/* Returns ancestors */
class Item_nodeset_func_ancestorbyname: public Item_nodeset_func_axisbyname
{
bool need_self;
public:
Item_nodeset_func_ancestorbyname(Item *a, const char *n_arg, uint l_arg,
String *pxml, bool need_self_arg):
Item_nodeset_func_axisbyname(a, n_arg, l_arg, pxml),
need_self(need_self_arg) {}
const char *func_name() const { return "xpath_ancestorbyname"; }
String *val_nodeset(String *nodeset);
};
/* Returns parents */
class Item_nodeset_func_parentbyname: public Item_nodeset_func_axisbyname
{
public:
Item_nodeset_func_parentbyname(Item *a, const char *n_arg, uint l_arg,
String *pxml):
Item_nodeset_func_axisbyname(a, n_arg, l_arg, pxml) {}
const char *func_name() const { return "xpath_parentbyname"; }
String *val_nodeset(String *nodeset);
};
/* Returns attributes */
class Item_nodeset_func_attributebyname: public Item_nodeset_func_axisbyname
{
public:
Item_nodeset_func_attributebyname(Item *a, const char *n_arg, uint l_arg,
String *pxml):
Item_nodeset_func_axisbyname(a, n_arg, l_arg, pxml) {}
const char *func_name() const { return "xpath_attributebyname"; }
String *val_nodeset(String *nodeset);
};
/*
Condition iterator: goes through all nodes in the current
context and checks a condition, returning those nodes
giving TRUE condition result.
*/
class Item_nodeset_func_predicate :public Item_nodeset_func
{
public:
Item_nodeset_func_predicate(Item *a, Item *b, String *pxml):
Item_nodeset_func(a, b, pxml) {}
const char *func_name() const { return "xpath_predicate"; }
String *val_nodeset(String *nodeset);
};
/* Selects nodes with a given position in context */
class Item_nodeset_func_elementbyindex :public Item_nodeset_func
{
public:
Item_nodeset_func_elementbyindex(Item *a, Item *b, String *pxml):
Item_nodeset_func(a, b, pxml) { }
const char *func_name() const { return "xpath_elementbyindex"; }
String *val_nodeset(String *nodeset);
};
/*
We need to distinguish a number from a boolean:
a[1] and a[true] are different things in XPath.
*/
class Item_bool :public Item_int
{
public:
Item_bool(int32 i): Item_int(i) {}
const char *func_name() const { return "xpath_bool"; }
bool is_bool_func() { return 1; }
};
/*
Converts its argument into a boolean value.
* a number is true if it is non-zero
* a node-set is true if and only if it is non-empty
* a string is true if and only if its length is non-zero
*/
class Item_xpath_cast_bool :public Item_int_func
{
String *pxml;
String tmp_value;
public:
Item_xpath_cast_bool(Item *a, String *pxml_arg)
:Item_int_func(a), pxml(pxml_arg) {}
const char *func_name() const { return "xpath_cast_bool"; }
bool is_bool_func() { return 1; }
longlong val_int()
{
if (args[0]->type() == XPATH_NODESET)
{
String *flt= args[0]->val_nodeset(&tmp_value);
return flt->length() == sizeof(MY_XPATH_FLT) ? 1 : 0;
}
return args[0]->val_real() ? 1 : 0;
}
};
/*
Converts its argument into a number
*/
class Item_xpath_cast_number :public Item_real_func
{
public:
Item_xpath_cast_number(Item *a): Item_real_func(a) {}
const char *func_name() const { return "xpath_cast_number"; }
virtual double val_real() { return args[0]->val_real(); }
};
/*
Context cache, for predicate
*/
class Item_nodeset_context_cache :public Item_nodeset_func
{
public:
String *string_cache;
Item_nodeset_context_cache(String *str_arg, String *pxml):
Item_nodeset_func(pxml), string_cache(str_arg) { }
String *val_nodeset(String *res)
{ return string_cache; }
void fix_length_and_dec() { max_length= MAX_BLOB_WIDTH; }
};
class Item_func_xpath_position :public Item_int_func
{
String *pxml;
String tmp_value;
public:
Item_func_xpath_position(Item *a, String *p)
:Item_int_func(a), pxml(p) {}
const char *func_name() const { return "xpath_position"; }
void fix_length_and_dec() { max_length=10; }
longlong val_int()
{
String *flt= args[0]->val_nodeset(&tmp_value);
if (flt->length() == sizeof(MY_XPATH_FLT))
return ((MY_XPATH_FLT*)flt->ptr())->pos + 1;
return 0;
}
};
class Item_func_xpath_count :public Item_int_func
{
String *pxml;
String tmp_value;
public:
Item_func_xpath_count(Item *a, String *p)
:Item_int_func(a), pxml(p) {}
const char *func_name() const { return "xpath_count"; }
void fix_length_and_dec() { max_length=10; }
longlong val_int()
{
uint predicate_supplied_context_size;
String *res= args[0]->val_nodeset(&tmp_value);
if (res->length() == sizeof(MY_XPATH_FLT) &&
(predicate_supplied_context_size= ((MY_XPATH_FLT*)res->ptr())->size))
return predicate_supplied_context_size;
return res->length() / sizeof(MY_XPATH_FLT);
}
};
class Item_func_xpath_sum :public Item_real_func
{
String *pxml;
String tmp_value;
public:
Item_func_xpath_sum(Item *a, String *p)
:Item_real_func(a), pxml(p) {}
const char *func_name() const { return "xpath_sum"; }
double val_real()
{
double sum= 0;
String *res= args[0]->val_nodeset(&tmp_value);
MY_XPATH_FLT *fltbeg= (MY_XPATH_FLT*) res->ptr();
MY_XPATH_FLT *fltend= (MY_XPATH_FLT*) (res->ptr() + res->length());
uint numnodes= pxml->length() / sizeof(MY_XML_NODE);
MY_XML_NODE *nodebeg= (MY_XML_NODE*) pxml->ptr();
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
MY_XML_NODE *self= &nodebeg[flt->num];
for (uint j= flt->num + 1; j < numnodes; j++)
{
MY_XML_NODE *node= &nodebeg[j];
if (node->level <= self->level)
break;
if ((node->parent == flt->num) &&
(node->type == MY_XML_NODE_TEXT))
{
char *end;
int err;
double add= my_strntod(collation.collation, (char*) node->beg,
node->end - node->beg, &end, &err);
if (!err)
sum+= add;
}
}
}
return sum;
}
};
class Item_nodeset_to_const_comparator :public Item_bool_func
{
String *pxml;
String tmp_nodeset;
public:
Item_nodeset_to_const_comparator(Item *nodeset, Item *cmpfunc, String *p)
:Item_bool_func(nodeset,cmpfunc), pxml(p) {}
enum Type type() const { return XPATH_NODESET_CMP; };
const char *func_name() const { return "xpath_nodeset_to_const_comparator"; }
bool is_bool_func() { return 1; }
longlong val_int()
{
Item_func *comp= (Item_func*)args[1];
Item_string *fake= (Item_string*)(comp->arguments()[0]);
String *res= args[0]->val_nodeset(&tmp_nodeset);
MY_XPATH_FLT *fltbeg= (MY_XPATH_FLT*) res->ptr();
MY_XPATH_FLT *fltend= (MY_XPATH_FLT*) (res->ptr() + res->length());
MY_XML_NODE *nodebeg= (MY_XML_NODE*) pxml->ptr();
uint numnodes= pxml->length() / sizeof(MY_XML_NODE);
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
MY_XML_NODE *self= &nodebeg[flt->num];
for (uint j= flt->num + 1; j < numnodes; j++)
{
MY_XML_NODE *node= &nodebeg[j];
if (node->level <= self->level)
break;
if ((node->parent == flt->num) &&
(node->type == MY_XML_NODE_TEXT))
{
fake->str_value.set(node->beg, node->end - node->beg,
collation.collation);
if (args[1]->val_int())
return 1;
}
}
}
return 0;
}
};
String *Item_nodeset_func_rootelement::val_nodeset(String *nodeset)
{
nodeset->length(0);
((XPathFilter*)nodeset)->append_element(0, 0);
return nodeset;
}
String * Item_nodeset_func_union::val_nodeset(String *nodeset)
{
uint numnodes= pxml->length() / sizeof(MY_XML_NODE);
String set0, *s0= args[0]->val_nodeset(&set0);
String set1, *s1= args[1]->val_nodeset(&set1);
String both_str;
both_str.alloc(numnodes);
char *both= (char*) both_str.ptr();
bzero((void*)both, numnodes);
MY_XPATH_FLT *flt;
fltbeg= (MY_XPATH_FLT*) s0->ptr();
fltend= (MY_XPATH_FLT*) (s0->ptr() + s0->length());
for (flt= fltbeg; flt < fltend; flt++)
both[flt->num]= 1;
fltbeg= (MY_XPATH_FLT*) s1->ptr();
fltend= (MY_XPATH_FLT*) (s1->ptr() + s1->length());
for (flt= fltbeg; flt < fltend; flt++)
both[flt->num]= 1;
nodeset->length(0);
for (uint i= 0, pos= 0; i < numnodes; i++)
{
if (both[i])
((XPathFilter*)nodeset)->append_element(i, pos++);
}
return nodeset;
}
String *Item_nodeset_func_selfbyname::val_nodeset(String *nodeset)
{
prepare(nodeset);
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
uint pos= 0;
MY_XML_NODE *self= &nodebeg[flt->num];
if (validname(self))
((XPathFilter*)nodeset)->append_element(flt->num,pos++);
}
return nodeset;
}
String *Item_nodeset_func_childbyname::val_nodeset(String *nodeset)
{
prepare(nodeset);
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
MY_XML_NODE *self= &nodebeg[flt->num];
for (uint pos= 0, j= flt->num + 1 ; j < numnodes; j++)
{
MY_XML_NODE *node= &nodebeg[j];
if (node->level <= self->level)
break;
if ((node->parent == flt->num) &&
(node->type == MY_XML_NODE_TAG) &&
validname(node))
((XPathFilter*)nodeset)->append_element(j, pos++);
}
}
return nodeset;
}
String *Item_nodeset_func_descendantbyname::val_nodeset(String *nodeset)
{
prepare(nodeset);
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
uint pos= 0;
MY_XML_NODE *self= &nodebeg[flt->num];
if (need_self && validname(self))
((XPathFilter*)nodeset)->append_element(flt->num,pos++);
for (uint j= flt->num + 1 ; j < numnodes ; j++)
{
MY_XML_NODE *node= &nodebeg[j];
if (node->level <= self->level)
break;
if ((node->type == MY_XML_NODE_TAG) && validname(node))
((XPathFilter*)nodeset)->append_element(j,pos++);
}
}
return nodeset;
}
String *Item_nodeset_func_ancestorbyname::val_nodeset(String *nodeset)
{
char *active;
String active_str;
prepare(nodeset);
active_str.alloc(numnodes);
active= (char*) active_str.ptr();
bzero((void*)active, numnodes);
uint pos= 0;
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
/*
Go to the root and add all nodes on the way.
Don't add the root if context is the root itelf
*/
MY_XML_NODE *self= &nodebeg[flt->num];
if (need_self && validname(self))
{
active[flt->num]= 1;
pos++;
}
for (uint j= self->parent; nodebeg[j].parent != j; j= nodebeg[j].parent)
{
if (flt->num && validname(&nodebeg[j]))
{
active[j]= 1;
pos++;
}
}
}
for (uint j= 0; j < numnodes ; j++)
{
if (active[j])
((XPathFilter*)nodeset)->append_element(j, --pos);
}
return nodeset;
}
String *Item_nodeset_func_parentbyname::val_nodeset(String *nodeset)
{
char *active;
String active_str;
prepare(nodeset);
active_str.alloc(numnodes);
active= (char*) active_str.ptr();
bzero((void*)active, numnodes);
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
uint j= nodebeg[flt->num].parent;
if (flt->num && validname(&nodebeg[j]))
active[j]= 1;
}
for (uint j= 0, pos= 0; j < numnodes ; j++)
{
if (active[j])
((XPathFilter*)nodeset)->append_element(j, pos++);
}
return nodeset;
}
String *Item_nodeset_func_attributebyname::val_nodeset(String *nodeset)
{
prepare(nodeset);
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
MY_XML_NODE *self= &nodebeg[flt->num];
for (uint pos=0, j= flt->num + 1 ; j < numnodes; j++)
{
MY_XML_NODE *node= &nodebeg[j];
if (node->level <= self->level)
break;
if ((node->parent == flt->num) &&
(node->type == MY_XML_NODE_ATTR) &&
validname(node))
((XPathFilter*)nodeset)->append_element(j, pos++);
}
}
return nodeset;
}
String *Item_nodeset_func_predicate::val_nodeset(String *str)
{
Item_nodeset_func *nodeset_func= (Item_nodeset_func*) args[0];
Item_func *comp_func= (Item_func*)args[1];
uint pos= 0, size;
prepare(str);
size= fltend - fltbeg;
for (MY_XPATH_FLT *flt= fltbeg; flt < fltend; flt++)
{
nodeset_func->context_cache.length(0);
((XPathFilter*)(&nodeset_func->context_cache))->append_element(flt->num,
flt->pos,
size);
if (comp_func->val_int())
((XPathFilter*)str)->append_element(flt->num, pos++);
}
return str;
}
String *Item_nodeset_func_elementbyindex::val_nodeset(String *nodeset)
{
Item_nodeset_func *nodeset_func= (Item_nodeset_func*) args[0];
prepare(nodeset);
MY_XPATH_FLT *flt;
uint pos, size= fltend - fltbeg;
for (pos= 0, flt= fltbeg; flt < fltend; flt++)
{
nodeset_func->context_cache.length(0);
((XPathFilter*)(&nodeset_func->context_cache))->append_element(flt->num,
flt->pos,
size);
int index= (int) (args[1]->val_int()) - 1;
if (index >= 0 && (flt->pos == (uint) index || args[1]->is_bool_func()))
((XPathFilter*)nodeset)->append_element(flt->num, pos++);
}
return nodeset;
}
/*
If item is a node set, then casts it to boolean,
otherwise returns the item itself.
*/
static Item* nodeset2bool(MY_XPATH *xpath, Item *item)
{
if (item->type() == Item::XPATH_NODESET)
return new Item_xpath_cast_bool(item, xpath->pxml);
return item;
}
/*
XPath lexical tokens
*/
#define MY_XPATH_LEX_DIGITS 'd'
#define MY_XPATH_LEX_IDENT 'i'
#define MY_XPATH_LEX_STRING 's'
#define MY_XPATH_LEX_SLASH '/'
#define MY_XPATH_LEX_LB '['
#define MY_XPATH_LEX_RB ']'
#define MY_XPATH_LEX_LP '('
#define MY_XPATH_LEX_RP ')'
#define MY_XPATH_LEX_EQ '='
#define MY_XPATH_LEX_LESS '<'
#define MY_XPATH_LEX_GREATER '>'
#define MY_XPATH_LEX_AT '@'
#define MY_XPATH_LEX_COLON ':'
#define MY_XPATH_LEX_ASTERISK '*'
#define MY_XPATH_LEX_DOT '.'
#define MY_XPATH_LEX_VLINE '|'
#define MY_XPATH_LEX_MINUS '-'
#define MY_XPATH_LEX_PLUS '+'
#define MY_XPATH_LEX_EXCL '!'
#define MY_XPATH_LEX_COMMA ','
#define MY_XPATH_LEX_DOLLAR '$'
#define MY_XPATH_LEX_ERROR 'A'
#define MY_XPATH_LEX_EOF 'B'
#define MY_XPATH_LEX_AND 'C'
#define MY_XPATH_LEX_OR 'D'
#define MY_XPATH_LEX_DIV 'E'
#define MY_XPATH_LEX_MOD 'F'
#define MY_XPATH_LEX_FUNC 'G'
#define MY_XPATH_LEX_NODETYPE 'H'
#define MY_XPATH_LEX_AXIS 'I'
#define MY_XPATH_LEX_LE 'J'
#define MY_XPATH_LEX_GE 'K'
/*
XPath axis type
*/
#define MY_XPATH_AXIS_ANCESTOR 0
#define MY_XPATH_AXIS_ANCESTOR_OR_SELF 1
#define MY_XPATH_AXIS_ATTRIBUTE 2
#define MY_XPATH_AXIS_CHILD 3
#define MY_XPATH_AXIS_DESCENDANT 4
#define MY_XPATH_AXIS_DESCENDANT_OR_SELF 5
#define MY_XPATH_AXIS_FOLLOWING 6
#define MY_XPATH_AXIS_FOLLOWING_SIBLING 7
#define MY_XPATH_AXIS_NAMESPACE 8
#define MY_XPATH_AXIS_PARENT 9
#define MY_XPATH_AXIS_PRECEDING 10
#define MY_XPATH_AXIS_PRECEDING_SIBLING 11
#define MY_XPATH_AXIS_SELF 12
/*
Create scalar comparator
SYNOPSYS
Create a comparator function for scalar arguments,
for the given arguments and operation.
RETURN
The newly created item.
*/
static Item *eq_func(int oper, Item *a, Item *b)
{
switch (oper)
{
case '=': return new Item_func_eq(a, b);
case '!': return new Item_func_ne(a, b);
case MY_XPATH_LEX_GE: return new Item_func_ge(a, b);
case MY_XPATH_LEX_LE: return new Item_func_le(a, b);
case MY_XPATH_LEX_GREATER: return new Item_func_gt(a, b);
case MY_XPATH_LEX_LESS: return new Item_func_lt(a, b);
}
return 0;
}
/*
Create scalar comparator
SYNOPSYS
Create a comparator function for scalar arguments,
for the given arguments and reverse operation, e.g.
A > B is converted into B < A
RETURN
The newly created item.
*/
static Item *eq_func_reverse(int oper, Item *a, Item *b)
{
switch (oper)
{
case '=': return new Item_func_eq(a, b);
case '!': return new Item_func_ne(a, b);
case MY_XPATH_LEX_GE: return new Item_func_le(a, b);
case MY_XPATH_LEX_LE: return new Item_func_ge(a, b);
case MY_XPATH_LEX_GREATER: return new Item_func_lt(a, b);
case MY_XPATH_LEX_LESS: return new Item_func_gt(a, b);
}
return 0;
}
/*
Create a comparator
SYNOPSYS
Create a comparator for scalar or non-scalar arguments,
for the given arguments and operation.
RETURN
The newly created item.
*/
static Item *create_comparator(MY_XPATH *xpath,
int oper, MY_XPATH_LEX *context,
Item *a, Item *b)
{
if (a->type() != Item::XPATH_NODESET &&
b->type() != Item::XPATH_NODESET)
{
return eq_func(oper, a, b); // two scalar arguments
}
else if (a->type() == Item::XPATH_NODESET &&
b->type() == Item::XPATH_NODESET)
{
uint len= context->end - context->beg;
set_if_bigger(len, 32);
my_printf_error(ER_UNKNOWN_ERROR,
"XPATH error: "
"comparison of two nodesets is not supported: '%.*s'",
MYF(0), len, context->beg);
return 0; // TODO: Comparison of two nodesets
}
else
{
/*
Compare a node set to a scalar value.
We just create a fake Item_string() argument,
which will be filled to the partular value
in a loop through all of the nodes in the node set.
*/
Item *fake= new Item_string("", 0, xpath->cs);
Item_nodeset_func *nodeset;
Item *scalar, *comp;
if (a->type() == Item::XPATH_NODESET)
{
nodeset= (Item_nodeset_func*) a;
scalar= b;
comp= eq_func(oper, fake, scalar);
}
else
{
nodeset= (Item_nodeset_func*) b;
scalar= a;
comp= eq_func_reverse(oper, fake, scalar);
}
return new Item_nodeset_to_const_comparator(nodeset, comp, xpath->pxml);
}
}
/*
Create a step
SYNOPSYS
Create a step function for the given argument and axis.
RETURN
The newly created item.
*/
static Item* nametestfunc(MY_XPATH *xpath,
int type, Item *arg, const char *beg, uint len)
{
DBUG_ASSERT(arg != 0);
DBUG_ASSERT(arg->type() == Item::XPATH_NODESET);
DBUG_ASSERT(beg != 0);
DBUG_ASSERT(len > 0);
Item *res;
switch (type)
{
case MY_XPATH_AXIS_ANCESTOR:
res= new Item_nodeset_func_ancestorbyname(arg, beg, len, xpath->pxml, 0);
break;
case MY_XPATH_AXIS_ANCESTOR_OR_SELF:
res= new Item_nodeset_func_ancestorbyname(arg, beg, len, xpath->pxml, 1);
break;
case MY_XPATH_AXIS_PARENT:
res= new Item_nodeset_func_parentbyname(arg, beg, len, xpath->pxml);
break;
case MY_XPATH_AXIS_DESCENDANT:
res= new Item_nodeset_func_descendantbyname(arg, beg, len, xpath->pxml, 0);
break;
case MY_XPATH_AXIS_DESCENDANT_OR_SELF:
res= new Item_nodeset_func_descendantbyname(arg, beg, len, xpath->pxml, 1);
break;
case MY_XPATH_AXIS_ATTRIBUTE:
res= new Item_nodeset_func_attributebyname(arg, beg, len, xpath->pxml);
break;
case MY_XPATH_AXIS_SELF:
res= new Item_nodeset_func_selfbyname(arg, beg, len, xpath->pxml);
break;
default:
res= new Item_nodeset_func_childbyname(arg, beg, len, xpath->pxml);
}
return res;
}
/*
Tokens consisting of one character, for faster lexical analizer.
*/
static char simpletok[128]=
{
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
/*
! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 5 6 7 8 9 : ; < = > ?
@ A B C D E F G H I J K L M N O P Q R S T U V W X Y Z [ \ ] ^ _
` a b c d e f g h i j k l m n o p q r s t u v w x y z { | } ~ <20>
*/
0,1,0,0,1,0,0,0,1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0,0,1,0,1,1,1,0,
1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,1,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0
};
/*
XPath keywords
*/
struct my_xpath_keyword_names_st
{
int tok;
const char *name;
size_t length;
int extra;
};
static struct my_xpath_keyword_names_st my_keyword_names[] =
{
{MY_XPATH_LEX_AND , "and" , 3, 0 },
{MY_XPATH_LEX_OR , "or" , 2, 0 },
{MY_XPATH_LEX_DIV , "div" , 3, 0 },
{MY_XPATH_LEX_MOD , "mod" , 3, 0 },
{0,NULL,0,0}
};
static struct my_xpath_keyword_names_st my_axis_names[]=
{
{MY_XPATH_LEX_AXIS,"ancestor" , 8,MY_XPATH_AXIS_ANCESTOR },
{MY_XPATH_LEX_AXIS,"ancestor-or-self" ,16,MY_XPATH_AXIS_ANCESTOR_OR_SELF },
{MY_XPATH_LEX_AXIS,"attribute" , 9,MY_XPATH_AXIS_ATTRIBUTE },
{MY_XPATH_LEX_AXIS,"child" , 5,MY_XPATH_AXIS_CHILD },
{MY_XPATH_LEX_AXIS,"descendant" ,10,MY_XPATH_AXIS_DESCENDANT },
{MY_XPATH_LEX_AXIS,"descendant-or-self",18,MY_XPATH_AXIS_DESCENDANT_OR_SELF},
{MY_XPATH_LEX_AXIS,"following" , 9,MY_XPATH_AXIS_FOLLOWING },
{MY_XPATH_LEX_AXIS,"following-sibling" ,17,MY_XPATH_AXIS_FOLLOWING_SIBLING },
{MY_XPATH_LEX_AXIS,"namespace" , 9,MY_XPATH_AXIS_NAMESPACE },
{MY_XPATH_LEX_AXIS,"parent" , 6,MY_XPATH_AXIS_PARENT },
{MY_XPATH_LEX_AXIS,"preceding" , 9,MY_XPATH_AXIS_PRECEDING },
{MY_XPATH_LEX_AXIS,"preceding-sibling" ,17,MY_XPATH_AXIS_PRECEDING_SIBLING },
{MY_XPATH_LEX_AXIS,"self" , 4,MY_XPATH_AXIS_SELF },
{0,NULL,0,0}
};
static struct my_xpath_keyword_names_st my_nodetype_names[]=
{
{MY_XPATH_LEX_NODETYPE, "comment" , 7, 0 },
{MY_XPATH_LEX_NODETYPE, "text" , 4, 0 },
{MY_XPATH_LEX_NODETYPE, "processing-instruction" , 22,0 },
{MY_XPATH_LEX_NODETYPE, "node" , 4, 0 },
{0,NULL,0,0}
};
/*
Lookup a keyword
SYNOPSYS
Check that the last scanned identifier is a keyword.
RETURN
- Token type, on lookup success.
- MY_XPATH_LEX_IDENT, on lookup failure.
*/
static int
my_xpath_keyword(MY_XPATH *x,
struct my_xpath_keyword_names_st *keyword_names,
const char *beg, const char *end)
{
struct my_xpath_keyword_names_st *k;
size_t length= end-beg;
for (k= keyword_names; k->name; k++)
{
if (length == k->length && !strncasecmp(beg, k->name, length))
{
x->extra= k->extra;
return k->tok;
}
}
return MY_XPATH_LEX_IDENT;
}
/*
Functions to create an item, a-la those in item_create.cc
*/
static Item *create_func_true(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_bool(1);
}
static Item *create_func_false(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_bool(0);
}
static Item *create_func_not(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_func_not(nodeset2bool(xpath, args[0]));
}
static Item *create_func_ceiling(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_func_ceiling(args[0]);
}
static Item *create_func_floor(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_func_floor(args[0]);
}
static Item *create_func_bool(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_xpath_cast_bool(args[0], xpath->pxml);
}
static Item *create_func_number(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_xpath_cast_number(args[0]);
}
static Item *create_func_string_length(MY_XPATH *xpath, Item **args, uint nargs)
{
Item *arg= nargs ? args[0] : xpath->context;
return arg ? new Item_func_char_length(arg) : 0;
}
static Item *create_func_round(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_func_round(args[0], new Item_int((char*)"0",0,1),0);
}
static Item *create_func_last(MY_XPATH *xpath, Item **args, uint nargs)
{
return xpath->context ?
new Item_func_xpath_count(xpath->context, xpath->pxml) : NULL;
}
static Item *create_func_position(MY_XPATH *xpath, Item **args, uint nargs)
{
return xpath->context ?
new Item_func_xpath_position(xpath->context, xpath->pxml) : NULL;
}
static Item *create_func_contains(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_xpath_cast_bool(new Item_func_locate(args[0], args[1]),
xpath->pxml);
}
static Item *create_func_concat(MY_XPATH *xpath, Item **args, uint nargs)
{
return new Item_func_concat(args[0], args[1]);
}
static Item *create_func_substr(MY_XPATH *xpath, Item **args, uint nargs)
{
if (nargs == 2)
return new Item_func_substr(args[0], args[1]);
else
return new Item_func_substr(args[0], args[1], args[2]);
}
static Item *create_func_count(MY_XPATH *xpath, Item **args, uint nargs)
{
if (args[0]->type() != Item::XPATH_NODESET)
return 0;
return new Item_func_xpath_count(args[0], xpath->pxml);
}
static Item *create_func_sum(MY_XPATH *xpath, Item **args, uint nargs)
{
if (args[0]->type() != Item::XPATH_NODESET)
return 0;
return new Item_func_xpath_sum(args[0], xpath->pxml);
}
/*
Functions names. Separate lists for names with
lengths 3,4,5 and 6 for faster lookups.
*/
static MY_XPATH_FUNC my_func_names3[]=
{
{"sum", 3, 1 , 1 , create_func_sum},
{"not", 3, 1 , 1 , create_func_not},
{0 , 0, 0 , 0, 0}
};
static MY_XPATH_FUNC my_func_names4[]=
{
{"last", 4, 0, 0, create_func_last},
{"true", 4, 0, 0, create_func_true},
{"name", 4, 0, 1, 0},
{"lang", 4, 1, 1, 0},
{0 , 0, 0, 0, 0}
};
static MY_XPATH_FUNC my_func_names5[]=
{
{"count", 5, 1, 1, create_func_count},
{"false", 5, 0, 0, create_func_false},
{"floor", 5, 1, 1, create_func_floor},
{"round", 5, 1, 1, create_func_round},
{0 , 0, 0, 0, 0}
};
static MY_XPATH_FUNC my_func_names6[]=
{
{"concat", 6, 2, 255, create_func_concat},
{"number", 6, 0, 1 , create_func_number},
{"string", 6, 0, 1 , 0},
{0 , 0, 0, 0 , 0}
};
/* Other functions, with name longer than 6, all together */
static MY_XPATH_FUNC my_func_names[] =
{
{"id" , 2 , 1 , 1 , 0},
{"boolean" , 7 , 1 , 1 , create_func_bool},
{"ceiling" , 7 , 1 , 1 , create_func_ceiling},
{"position" , 8 , 0 , 0 , create_func_position},
{"contains" , 8 , 2 , 2 , create_func_contains},
{"substring" , 9 , 2 , 3 , create_func_substr},
{"translate" , 9 , 3 , 3 , 0},
{"local-name" , 10 , 0 , 1 , 0},
{"starts-with" , 11 , 2 , 2 , 0},
{"namespace-uri" , 13 , 0 , 1 , 0},
{"string-length" , 13 , 0 , 1 , create_func_string_length},
{"substring-after" , 15 , 2 , 2 , 0},
{"normalize-space" , 15 , 0 , 1 , 0},
{"substring-before" , 16 , 2 , 2 , 0},
{NULL,0,0,0,0}
};
/*
Lookup a function by name
SYNOPSYS
Lookup a function by its name.
RETURN
Pointer to a MY_XPATH_FUNC variable on success.
0 - on failure.
*/
MY_XPATH_FUNC *
my_xpath_function(const char *beg, const char *end)
{
MY_XPATH_FUNC *k, *function_names;
uint length= end-beg;
switch (length)
{
case 1: return 0;
case 3: function_names= my_func_names3; break;
case 4: function_names= my_func_names4; break;
case 5: function_names= my_func_names5; break;
case 6: function_names= my_func_names6; break;
default: function_names= my_func_names;
}
for (k= function_names; k->name; k++)
if (k->create && length == k->length && !strncasecmp(beg, k->name, length))
return k;
return NULL;
}
/* Initialize a lex analizer token */
static void
my_xpath_lex_init(MY_XPATH_LEX *lex,
const char *str, const char *strend)
{
lex->beg= str;
lex->end= strend;
}
/* Initialize an XPath query parser */
static void
my_xpath_init(MY_XPATH *xpath)
{
bzero((void*)xpath, sizeof(xpath[0]));
}
static int
my_xdigit(int c)
{
return ((c) >= '0' && (c) <= '9');
}
/*
Scan the next token
SYNOPSYS
Scan the next token from the input.
lex->term is set to the scanned token type.
lex->beg and lex->end are set to the beginnig
and to the end of the token.
RETURN
N/A
*/
static void
my_xpath_lex_scan(MY_XPATH *xpath,
MY_XPATH_LEX *lex, const char *beg, const char *end)
{
int ch, ctype, length;
for ( ; beg < end && *beg == ' ' ; beg++); // skip leading spaces
lex->beg= beg;
if (beg >= end)
{
lex->end= beg;
lex->term= MY_XPATH_LEX_EOF; // end of line reached
return;
}
// Check ident, or a function call, or a keyword
if ((length= xpath->cs->cset->ctype(xpath->cs, &ctype,
(const uchar*) beg,
(const uchar*) end)) > 0 &&
((ctype & (_MY_L | _MY_U)) || *beg == '_'))
{
// scan untill the end of the idenfitier
for (beg+= length;
(length= xpath->cs->cset->ctype(xpath->cs, &ctype,
(const uchar*) beg,
(const uchar*) end)) > 0 &&
((ctype & (_MY_L | _MY_U | _MY_NMR)) ||
*beg == '_' || *beg == '-' || *beg == '.') ;
beg+= length) /* no op */;
lex->end= beg;
if (beg < end)
{
if (*beg == '(')
{
/*
check if a function call, e.g.: count(/a/b)
or a nodetype test, e.g.: /a/b/text()
*/
if ((xpath->func= my_xpath_function(lex->beg, beg)))
lex->term= MY_XPATH_LEX_FUNC;
else
lex->term= my_xpath_keyword(xpath, my_nodetype_names,
lex->beg, beg);
return;
}
// check if an axis specifier, e.g.: /a/b/child::*
else if (*beg == ':' && beg + 1 < end && beg[1] == ':')
{
lex->term= my_xpath_keyword(xpath, my_axis_names,
lex->beg, beg);
return;
}
}
// check if a keyword
lex->term= my_xpath_keyword(xpath, my_keyword_names,
lex->beg, beg);
return;
}
ch= *beg++;
if (ch > 0 && ch < 128 && simpletok[ch])
{
// a token consisting of one character found
lex->end= beg;
lex->term= ch;
return;
}
if (my_xdigit(ch)) // a sequence of digits
{
for ( ; beg < end && my_xdigit(*beg) ; beg++);
lex->end= beg;
lex->term= MY_XPATH_LEX_DIGITS;
return;
}
if (ch == '"' || ch == '\'') // a string: either '...' or "..."
{
for ( ; beg < end && *beg != ch ; beg++);
if (beg < end)
{
lex->end= beg+1;
lex->term= MY_XPATH_LEX_STRING;
return;
}
else
{
// unexpected end-of-line, without closing quot sign
lex->end= end;
lex->term= MY_XPATH_LEX_ERROR;
return;
}
}
lex->end= beg;
lex->term= MY_XPATH_LEX_ERROR; // unknown character
return;
}
/*
Scan the given token
SYNOPSYS
Scan the given token and rotate lasttok to prevtok on success.
RETURN
1 - success
0 - failure
*/
static int
my_xpath_parse_term(MY_XPATH *xpath, int term)
{
if (xpath->lasttok.term == term && !xpath->error)
{
xpath->prevtok= xpath->lasttok;
my_xpath_lex_scan(xpath, &xpath->lasttok,
xpath->lasttok.end, xpath->query.end);
return 1;
}
return 0;
}
/*
Scan AxisName
SYNOPSYS
Scan an axis name and store the scanned axis type into xpath->axis.
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_AxisName(MY_XPATH *xpath)
{
int rc= my_xpath_parse_term(xpath, MY_XPATH_LEX_AXIS);
xpath->axis= xpath->extra;
return rc;
}
/*********************************************
** Grammar rules, according to http://www.w3.org/TR/xpath
** Implemented using recursive descendant method.
** All the following grammar processing functions accept
** a signle "xpath" argument and return 1 on success and 0 on error.
** They also modify "xpath" argument by creating new items.
*/
/* [9] PredicateExpr ::= Expr */
#define my_xpath_parse_PredicateExpr(x) my_xpath_parse_Expr((x))
/* [14] Expr ::= OrExpr */
#define my_xpath_parse_Expr(x) my_xpath_parse_OrExpr((x))
static int my_xpath_parse_LocationPath(MY_XPATH *xpath);
static int my_xpath_parse_AbsoluteLocationPath(MY_XPATH *xpath);
static int my_xpath_parse_RelativeLocationPath(MY_XPATH *xpath);
static int my_xpath_parse_AbbreviatedStep(MY_XPATH *xpath);
static int my_xpath_parse_Step(MY_XPATH *xpath);
static int my_xpath_parse_AxisSpecifier(MY_XPATH *xpath);
static int my_xpath_parse_NodeTest(MY_XPATH *xpath);
static int my_xpath_parse_AbbreviatedAxisSpecifier(MY_XPATH *xpath);
static int my_xpath_parse_NameTest(MY_XPATH *xpath);
static int my_xpath_parse_FunctionCall(MY_XPATH *xpath);
static int my_xpath_parse_Number(MY_XPATH *xpath);
static int my_xpath_parse_FilterExpr(MY_XPATH *xpath);
static int my_xpath_parse_PathExpr(MY_XPATH *xpath);
static int my_xpath_parse_OrExpr(MY_XPATH *xpath);
static int my_xpath_parse_UnaryExpr(MY_XPATH *xpath);
static int my_xpath_parse_MultiplicativeExpr(MY_XPATH *xpath);
static int my_xpath_parse_AdditiveExpr(MY_XPATH *xpath);
static int my_xpath_parse_RelationalExpr(MY_XPATH *xpath);
static int my_xpath_parse_AndExpr(MY_XPATH *xpath);
static int my_xpath_parse_EqualityExpr(MY_XPATH *xpath);
static int my_xpath_parse_VariableReference(MY_XPATH *xpath);
/*
Scan LocationPath
SYNOPSYS
[1] LocationPath ::= RelativeLocationPath
| AbsoluteLocationPath
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_LocationPath(MY_XPATH *xpath)
{
Item *context= xpath->context;
if (!xpath->context)
xpath->context= xpath->rootelement;
int rc= my_xpath_parse_RelativeLocationPath(xpath) ||
my_xpath_parse_AbsoluteLocationPath(xpath);
xpath->item= xpath->context;
xpath->context= context;
return rc;
}
/*
Scan Absolute Location Path
SYNOPSYS
[2] AbsoluteLocationPath ::= '/' RelativeLocationPath?
| AbbreviatedAbsoluteLocationPath
[10] AbbreviatedAbsoluteLocationPath ::= '//' RelativeLocationPath
We combine these two rules into one rule for better performance:
[2,10] AbsoluteLocationPath ::= '/' RelativeLocationPath?
| '//' RelativeLocationPath
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_AbsoluteLocationPath(MY_XPATH *xpath)
{
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_SLASH))
return 0;
xpath->context= xpath->rootelement;
if (my_xpath_parse_term(xpath, MY_XPATH_LEX_SLASH))
{
xpath->context= new Item_nodeset_func_descendantbyname(xpath->context,
"*", 1,
xpath->pxml, 1);
return my_xpath_parse_RelativeLocationPath(xpath);
}
my_xpath_parse_RelativeLocationPath(xpath);
return (xpath->error == 0);
}
/*
Scan Relative Location Path
SYNOPSYS
For better performance we combine these two rules
[3] RelativeLocationPath ::= Step
| RelativeLocationPath '/' Step
| AbbreviatedRelativeLocationPath
[11] AbbreviatedRelativeLocationPath ::= RelativeLocationPath '//' Step
Into this one:
[3-11] RelativeLocationPath ::= Step
| RelativeLocationPath '/' Step
| RelativeLocationPath '//' Step
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_RelativeLocationPath(MY_XPATH *xpath)
{
if (!my_xpath_parse_Step(xpath))
return 0;
while (my_xpath_parse_term(xpath, MY_XPATH_LEX_SLASH))
{
if (my_xpath_parse_term(xpath, MY_XPATH_LEX_SLASH))
xpath->context= new Item_nodeset_func_descendantbyname(xpath->context,
"*", 1,
xpath->pxml, 1);
if (!my_xpath_parse_Step(xpath))
{
xpath->error= 1;
return 0;
}
}
return 1;
}
/*
Scan non-abbreviated or abbreviated Step
SYNOPSYS
[4] Step ::= AxisSpecifier NodeTest Predicate*
| AbbreviatedStep
[8] Predicate ::= '[' PredicateExpr ']'
RETURN
1 - success
0 - failure
*/
static int
my_xpath_parse_AxisSpecifier_NodeTest_opt_Predicate_list(MY_XPATH *xpath)
{
if (!my_xpath_parse_AxisSpecifier(xpath))
return 0;
if (!my_xpath_parse_NodeTest(xpath))
return 0;
while (my_xpath_parse_term(xpath, MY_XPATH_LEX_LB))
{
Item *prev_context= xpath->context;
String *context_cache;
context_cache= &((Item_nodeset_func*)xpath->context)->context_cache;
xpath->context= new Item_nodeset_context_cache(context_cache, xpath->pxml);
xpath->context_cache= context_cache;
if(!my_xpath_parse_PredicateExpr(xpath))
{
xpath->error= 1;
return 0;
}
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_RB))
{
xpath->error= 1;
return 0;
}
xpath->item= nodeset2bool(xpath, xpath->item);
if (xpath->item->is_bool_func())
{
xpath->context= new Item_nodeset_func_predicate(prev_context,
xpath->item,
xpath->pxml);
}
else
{
xpath->context= new Item_nodeset_func_elementbyindex(prev_context,
xpath->item,
xpath->pxml);
}
}
return 1;
}
static int my_xpath_parse_Step(MY_XPATH *xpath)
{
return
my_xpath_parse_AxisSpecifier_NodeTest_opt_Predicate_list(xpath) ||
my_xpath_parse_AbbreviatedStep(xpath);
}
/*
Scan Abbreviated Axis Specifier
SYNOPSYS
[5] AxisSpecifier ::= AxisName '::'
| AbbreviatedAxisSpecifier
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_AbbreviatedAxisSpecifier(MY_XPATH *xpath)
{
if (my_xpath_parse_term(xpath, MY_XPATH_LEX_AT))
xpath->axis= MY_XPATH_AXIS_ATTRIBUTE;
else
xpath->axis= MY_XPATH_AXIS_CHILD;
return 1;
}
/*
Scan non-abbreviated axis specifier
SYNOPSYS
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_AxisName_colon_colon(MY_XPATH *xpath)
{
return my_xpath_parse_AxisName(xpath) &&
my_xpath_parse_term(xpath, MY_XPATH_LEX_COLON) &&
my_xpath_parse_term(xpath, MY_XPATH_LEX_COLON);
}
/*
Scan Abbreviated AxisSpecifier
SYNOPSYS
[13] AbbreviatedAxisSpecifier ::= '@'?
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_AxisSpecifier(MY_XPATH *xpath)
{
return my_xpath_parse_AxisName_colon_colon(xpath) ||
my_xpath_parse_AbbreviatedAxisSpecifier(xpath);
}
/*
Scan NodeType followed by parens
SYNOPSYS
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_NodeTest_lp_rp(MY_XPATH *xpath)
{
return my_xpath_parse_term(xpath, MY_XPATH_LEX_NODETYPE) &&
my_xpath_parse_term(xpath, MY_XPATH_LEX_LP) &&
my_xpath_parse_term(xpath, MY_XPATH_LEX_RP);
}
/*
Scan NodeTest
SYNOPSYS
[7] NodeTest ::= NameTest
| NodeType '(' ')'
| 'processing-instruction' '(' Literal ')'
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_NodeTest(MY_XPATH *xpath)
{
return my_xpath_parse_NameTest(xpath) ||
my_xpath_parse_NodeTest_lp_rp(xpath);
}
/*
Scan Abbreviated Step
SYNOPSYS
[12] AbbreviatedStep ::= '.' | '..'
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_AbbreviatedStep(MY_XPATH *xpath)
{
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_DOT))
return 0;
if (my_xpath_parse_term(xpath, MY_XPATH_LEX_DOT))
xpath->context= new Item_nodeset_func_parentbyname(xpath->context, "*", 1,
xpath->pxml);
return 1;
}
/*
Scan Primary Expression
SYNOPSYS
[15] PrimaryExpr ::= VariableReference
| '(' Expr ')'
| Literal
| Number
| FunctionCall
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_lp_Expr_rp(MY_XPATH *xpath)
{
return my_xpath_parse_term(xpath, MY_XPATH_LEX_LP) &&
my_xpath_parse_Expr(xpath) &&
my_xpath_parse_term(xpath, MY_XPATH_LEX_RP);
}
static int my_xpath_parse_PrimaryExpr_literal(MY_XPATH *xpath)
{
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_STRING))
return 0;
xpath->item= new Item_string(xpath->prevtok.beg + 1,
xpath->prevtok.end - xpath->prevtok.beg - 2,
xpath->cs);
return 1;
}
static int my_xpath_parse_PrimaryExpr(MY_XPATH *xpath)
{
return
my_xpath_parse_lp_Expr_rp(xpath) ||
my_xpath_parse_VariableReference(xpath) ||
my_xpath_parse_PrimaryExpr_literal(xpath) ||
my_xpath_parse_Number(xpath) ||
my_xpath_parse_FunctionCall(xpath);
}
/*
Scan Function Call
SYNOPSYS
[16] FunctionCall ::= FunctionName '(' ( Argument ( ',' Argument )* )? ')'
[17] Argument ::= Expr
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_FunctionCall(MY_XPATH *xpath)
{
Item *args[256];
uint nargs;
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_FUNC))
return 0;
MY_XPATH_FUNC *func= xpath->func;
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_LP))
return 0;
for (nargs= 0 ; nargs < func->maxargs; )
{
if (!my_xpath_parse_Expr(xpath))
{
if (nargs < func->minargs)
return 0;
goto right_paren;
}
args[nargs++]= xpath->item;
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_COMMA))
{
if (nargs < func->minargs)
return 0;
else
break;
}
}
right_paren:
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_RP))
return 0;
return ((xpath->item= func->create(xpath, args, nargs))) ? 1 : 0;
}
/*
Scan Union Expression
SYNOPSYS
[18] UnionExpr ::= PathExpr
| UnionExpr '|' PathExpr
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_UnionExpr(MY_XPATH *xpath)
{
if (!my_xpath_parse_PathExpr(xpath))
return 0;
while (my_xpath_parse_term(xpath, MY_XPATH_LEX_VLINE))
{
Item *prev= xpath->item;
if (prev->type() != Item::XPATH_NODESET)
return 0;
if (!my_xpath_parse_PathExpr(xpath)
|| xpath->item->type() != Item::XPATH_NODESET)
{
xpath->error= 1;
return 0;
}
xpath->item= new Item_nodeset_func_union(prev, xpath->item, xpath->pxml);
}
return 1;
}
/*
Scan Path Expression
SYNOPSYS
[19] PathExpr ::= LocationPath
| FilterExpr
| FilterExpr '/' RelativeLocationPath
| FilterExpr '//' RelativeLocationPath
RETURN
1 - success
0 - failure
*/
static int
my_xpath_parse_FilterExpr_opt_slashes_RelativeLocationPath(MY_XPATH *xpath)
{
if (!my_xpath_parse_FilterExpr(xpath))
return 0;
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_SLASH))
return 1;
my_xpath_parse_term(xpath, MY_XPATH_LEX_SLASH);
return my_xpath_parse_RelativeLocationPath(xpath);
}
static int my_xpath_parse_PathExpr(MY_XPATH *xpath)
{
return my_xpath_parse_LocationPath(xpath) ||
my_xpath_parse_FilterExpr_opt_slashes_RelativeLocationPath(xpath);
}
/*
Scan Filter Expression
SYNOPSYS
[20] FilterExpr ::= PrimaryExpr
| FilterExpr Predicate
or in other words:
[20] FilterExpr ::= PrimaryExpr Predicate*
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_FilterExpr(MY_XPATH *xpath)
{
return my_xpath_parse_PrimaryExpr(xpath);
}
/*
Scan Or Expression
SYNOPSYS
[21] OrExpr ::= AndExpr
| OrExpr 'or' AndExpr
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_OrExpr(MY_XPATH *xpath)
{
if (!my_xpath_parse_AndExpr(xpath))
return 0;
while (my_xpath_parse_term(xpath, MY_XPATH_LEX_OR))
{
Item *prev= xpath->item;
if (!my_xpath_parse_AndExpr(xpath))
{
return 0;
xpath->error= 1;
}
xpath->item= new Item_cond_or(nodeset2bool(xpath, prev),
nodeset2bool(xpath, xpath->item));
}
return 1;
}
/*
Scan And Expression
SYNOPSYS
[22] AndExpr ::= EqualityExpr
| AndExpr 'and' EqualityExpr
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_AndExpr(MY_XPATH *xpath)
{
if (!my_xpath_parse_EqualityExpr(xpath))
return 0;
while (my_xpath_parse_term(xpath, MY_XPATH_LEX_AND))
{
Item *prev= xpath->item;
if (!my_xpath_parse_EqualityExpr(xpath))
{
xpath->error= 1;
return 0;
}
xpath->item= new Item_cond_and(nodeset2bool(xpath,prev),
nodeset2bool(xpath,xpath->item));
}
return 1;
}
/*
Scan Equality Expression
SYNOPSYS
[23] EqualityExpr ::= RelationalExpr
| EqualityExpr '=' RelationalExpr
| EqualityExpr '!=' RelationalExpr
or in other words:
[23] EqualityExpr ::= RelationalExpr ( EqualityOperator EqualityExpr )*
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_ne(MY_XPATH *xpath)
{
MY_XPATH_LEX prevtok= xpath->prevtok;
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_EXCL))
return 0;
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_EQ))
{
/* Unget the exclamation mark */
xpath->lasttok= xpath->prevtok;
xpath->prevtok= prevtok;
return 0;
}
return 1;
}
static int my_xpath_parse_EqualityOperator(MY_XPATH *xpath)
{
if (my_xpath_parse_ne(xpath))
{
xpath->extra= '!';
return 1;
}
if (my_xpath_parse_term(xpath, MY_XPATH_LEX_EQ))
{
xpath->extra= '=';
return 1;
}
return 0;
}
static int my_xpath_parse_EqualityExpr(MY_XPATH *xpath)
{
MY_XPATH_LEX operator_context;
if (!my_xpath_parse_RelationalExpr(xpath))
return 0;
operator_context= xpath->lasttok;
while (my_xpath_parse_EqualityOperator(xpath))
{
Item *prev= xpath->item;
int oper= xpath->extra;
if (!my_xpath_parse_RelationalExpr(xpath))
{
xpath->error= 1;
return 0;
}
if (!(xpath->item= create_comparator(xpath, oper, &operator_context,
prev, xpath->item)))
return 0;
operator_context= xpath->lasttok;
}
return 1;
}
/*
Scan Relational Expression
SYNOPSYS
[24] RelationalExpr ::= AdditiveExpr
| RelationalExpr '<' AdditiveExpr
| RelationalExpr '>' AdditiveExpr
| RelationalExpr '<=' AdditiveExpr
| RelationalExpr '>=' AdditiveExpr
or in other words:
[24] RelationalExpr ::= AdditiveExpr (RelationalOperator RelationalExpr)*
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_RelationalOperator(MY_XPATH *xpath)
{
if (my_xpath_parse_term(xpath, MY_XPATH_LEX_LESS))
{
xpath->extra= my_xpath_parse_term(xpath, MY_XPATH_LEX_EQ) ?
MY_XPATH_LEX_LE : MY_XPATH_LEX_LESS;
return 1;
}
else if (my_xpath_parse_term(xpath, MY_XPATH_LEX_GREATER))
{
xpath->extra= my_xpath_parse_term(xpath, MY_XPATH_LEX_EQ) ?
MY_XPATH_LEX_GE : MY_XPATH_LEX_GREATER;
return 1;
}
return 0;
}
static int my_xpath_parse_RelationalExpr(MY_XPATH *xpath)
{
MY_XPATH_LEX operator_context;
if (!my_xpath_parse_AdditiveExpr(xpath))
return 0;
operator_context= xpath->lasttok;
while (my_xpath_parse_RelationalOperator(xpath))
{
Item *prev= xpath->item;
int oper= xpath->extra;
if (!my_xpath_parse_AdditiveExpr(xpath))
{
xpath->error= 1;
return 0;
}
if (!(xpath->item= create_comparator(xpath, oper, &operator_context,
prev, xpath->item)))
return 0;
operator_context= xpath->lasttok;
}
return 1;
}
/*
Scan Additive Expression
SYNOPSYS
[25] AdditiveExpr ::= MultiplicativeExpr
| AdditiveExpr '+' MultiplicativeExpr
| AdditiveExpr '-' MultiplicativeExpr
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_AdditiveOperator(MY_XPATH *xpath)
{
return my_xpath_parse_term(xpath, MY_XPATH_LEX_PLUS) ||
my_xpath_parse_term(xpath, MY_XPATH_LEX_MINUS);
}
static int my_xpath_parse_AdditiveExpr(MY_XPATH *xpath)
{
if (!my_xpath_parse_MultiplicativeExpr(xpath))
return 0;
while (my_xpath_parse_AdditiveOperator(xpath))
{
int oper= xpath->prevtok.term;
Item *prev= xpath->item;
if (!my_xpath_parse_MultiplicativeExpr(xpath))
{
xpath->error= 1;
return 0;
}
if (oper == MY_XPATH_LEX_PLUS)
xpath->item= new Item_func_plus(prev, xpath->item);
else
xpath->item= new Item_func_minus(prev, xpath->item);
};
return 1;
}
/*
Scan Multiplicative Expression
SYNOPSYS
[26] MultiplicativeExpr ::= UnaryExpr
| MultiplicativeExpr MultiplyOperator UnaryExpr
| MultiplicativeExpr 'div' UnaryExpr
| MultiplicativeExpr 'mod' UnaryExpr
or in other words:
[26] MultiplicativeExpr ::= UnaryExpr (MulOper MultiplicativeExpr)*
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_MultiplicativeOperator(MY_XPATH *xpath)
{
return
my_xpath_parse_term(xpath, MY_XPATH_LEX_ASTERISK) ||
my_xpath_parse_term(xpath, MY_XPATH_LEX_DIV) ||
my_xpath_parse_term(xpath, MY_XPATH_LEX_MOD);
}
static int my_xpath_parse_MultiplicativeExpr(MY_XPATH *xpath)
{
if (!my_xpath_parse_UnaryExpr(xpath))
return 0;
while (my_xpath_parse_MultiplicativeOperator(xpath))
{
int oper= xpath->prevtok.term;
Item *prev= xpath->item;
if (!my_xpath_parse_UnaryExpr(xpath))
{
xpath->error= 1;
return 0;
}
switch (oper)
{
case MY_XPATH_LEX_ASTERISK:
xpath->item= new Item_func_mul(prev, xpath->item);
break;
case MY_XPATH_LEX_DIV:
xpath->item= new Item_func_int_div(prev, xpath->item);
break;
case MY_XPATH_LEX_MOD:
xpath->item= new Item_func_mod(prev, xpath->item);
break;
}
}
return 1;
}
/*
Scan Unary Expression
SYNOPSYS
[27] UnaryExpr ::= UnionExpr
| '-' UnaryExpr
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_UnaryExpr(MY_XPATH *xpath)
{
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_MINUS))
return my_xpath_parse_UnionExpr(xpath);
if (!my_xpath_parse_UnaryExpr(xpath))
return 0;
xpath->item= new Item_func_neg(xpath->item);
return 1;
}
/*
Scan Number
SYNOPSYS
[30] Number ::= Digits ('.' Digits?)? | '.' Digits)
or in other words:
[30] Number ::= Digits
| Digits '.'
| Digits '.' Digits
| '.' Digits
Note: the last rule is not supported yet,
as it is in conflict with abbreviated step.
1 + .123 does not work,
1 + 0.123 does.
Perhaps it is better to move this code into lex analizer.
RETURN
1 - success
0 - failure
*/
static int my_xpath_parse_Number(MY_XPATH *xpath)
{
const char *beg;
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_DIGITS))
return 0;
beg= xpath->prevtok.beg;
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_DOT))
{
xpath->item= new Item_int(xpath->prevtok.beg,
xpath->prevtok.end - xpath->prevtok.beg);
return 1;
}
my_xpath_parse_term(xpath, MY_XPATH_LEX_DIGITS);
xpath->item= new Item_float(beg, xpath->prevtok.end - beg);
return 1;
}
/*
Scan NCName.
SYNOPSYS
The keywords AND, OR, MOD, DIV are valid identitiers
when they are in identifier context:
SELECT
ExtractValue('<and><or><mod><div>VALUE</div></mod></or></and>',
'/and/or/mod/div')
-> VALUE
RETURN
1 - success
0 - failure
*/
static int
my_xpath_parse_NCName(MY_XPATH *xpath)
{
return
my_xpath_parse_term(xpath, MY_XPATH_LEX_IDENT) ||
my_xpath_parse_term(xpath, MY_XPATH_LEX_AND) ||
my_xpath_parse_term(xpath, MY_XPATH_LEX_OR) ||
my_xpath_parse_term(xpath, MY_XPATH_LEX_MOD) ||
my_xpath_parse_term(xpath, MY_XPATH_LEX_DIV) ? 1 : 0;
}
/*
QName grammar can be found in a separate document
http://www.w3.org/TR/REC-xml-names/#NT-QName
[6] QName ::= (Prefix ':')? LocalPart
[7] Prefix ::= NCName
[8] LocalPart ::= NCName
*/
static int
my_xpath_parse_QName(MY_XPATH *xpath)
{
const char *beg;
if (!my_xpath_parse_NCName(xpath))
return 0;
beg= xpath->prevtok.beg;
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_COLON))
return 1; /* Non qualified name */
if (!my_xpath_parse_NCName(xpath))
return 0;
xpath->prevtok.beg= beg;
return 1;
}
/*
Scan Variable reference
SYNOPSYS
[36] VariableReference ::= '$' QName
RETURN
1 - success
0 - failure
*/
static int
my_xpath_parse_VariableReference(MY_XPATH *xpath)
{
return my_xpath_parse_term(xpath, MY_XPATH_LEX_DOLLAR) &&
my_xpath_parse_term(xpath, MY_XPATH_LEX_IDENT);
}
/*
Scan Name Test
SYNOPSYS
[37] NameTest ::= '*'
| NCName ':' '*'
| QName
RETURN
1 - success
0 - failure
*/
static int
my_xpath_parse_NodeTest_QName(MY_XPATH *xpath)
{
if (!my_xpath_parse_QName(xpath))
return 0;
DBUG_ASSERT(xpath->context);
uint len= xpath->prevtok.end - xpath->prevtok.beg;
xpath->context= nametestfunc(xpath, xpath->axis, xpath->context,
xpath->prevtok.beg, len);
return 1;
}
static int
my_xpath_parse_NodeTest_asterisk(MY_XPATH *xpath)
{
if (!my_xpath_parse_term(xpath, MY_XPATH_LEX_ASTERISK))
return 0;
DBUG_ASSERT(xpath->context);
xpath->context= nametestfunc(xpath, xpath->axis, xpath->context, "*", 1);
return 1;
}
static int
my_xpath_parse_NameTest(MY_XPATH *xpath)
{
return my_xpath_parse_NodeTest_asterisk(xpath) ||
my_xpath_parse_NodeTest_QName(xpath);
}
/*
Scan an XPath expression
SYNOPSYS
Scan xpath expression.
The expression is returned in xpath->expr.
RETURN
1 - success
0 - failure
*/
static int
my_xpath_parse(MY_XPATH *xpath, const char *str, const char *strend)
{
my_xpath_lex_init(&xpath->query, str, strend);
my_xpath_lex_init(&xpath->prevtok, str, strend);
my_xpath_lex_scan(xpath, &xpath->lasttok, str, strend);
xpath->rootelement= new Item_nodeset_func_rootelement(xpath->pxml);
return
my_xpath_parse_Expr(xpath) &&
my_xpath_parse_term(xpath, MY_XPATH_LEX_EOF);
}
void Item_xml_str_func::fix_length_and_dec()
{
String *xp, tmp;
MY_XPATH xpath;
int rc;
nodeset_func= 0;
if (agg_arg_charsets(collation, args, arg_count, MY_COLL_CMP_CONV, 1))
return;
if (collation.collation->mbminlen > 1)
{
/* UCS2 is not supported */
my_printf_error(ER_UNKNOWN_ERROR,
"Character set '%s' is not supported by XPATH",
MYF(0), collation.collation->csname);
return;
}
if (!args[1]->const_item())
{
my_printf_error(ER_UNKNOWN_ERROR,
"Only constant XPATH queries are supported", MYF(0));
return;
}
xp= args[1]->val_str(&tmp);
my_xpath_init(&xpath);
xpath.cs= collation.collation;
xpath.debug= 0;
xpath.pxml= &pxml;
pxml.set_charset(collation.collation);
rc= my_xpath_parse(&xpath, xp->ptr(), xp->ptr() + xp->length());
if (!rc)
{
char context[32];
uint clen= xpath.query.end - xpath.lasttok.beg;
set_if_bigger(clen, sizeof(context) - 1);
strmake(context, xpath.lasttok.beg, clen);
my_printf_error(ER_UNKNOWN_ERROR, "XPATH syntax error: '%s'",
MYF(0), context);
return;
}
nodeset_func= xpath.item;
if (nodeset_func)
nodeset_func->fix_fields(current_thd, &nodeset_func);
max_length= MAX_BLOB_WIDTH;
}
#define MAX_LEVEL 256
typedef struct
{
uint level;
String *pxml; // parsed XML
uint pos[MAX_LEVEL]; // Tag position stack
} MY_XML_USER_DATA;
/*
Find the parent node
SYNOPSYS
Find the parent node, i.e. a tag or attrubute node on the given level.
RETURN
1 - success
0 - failure
*/
static uint xml_parent_tag(MY_XML_NODE *items, uint nitems, uint level)
{
if (!nitems)
return 0;
MY_XML_NODE *p, *last= &items[nitems-1];
for (p= last; p >= items; p--)
{
if (p->level == level &&
(p->type == MY_XML_NODE_TAG ||
p->type == MY_XML_NODE_ATTR))
{
return p - items;
}
}
return 0;
}
/*
Process tag beginning
SYNOPSYS
A call-back function executed when XML parser
is entering a tag or an attribue.
Appends the new node into data->pxml.
Increments data->level.
RETURN
Currently only MY_XML_OK
*/
static int xml_enter(MY_XML_PARSER *st,const char *attr, size_t len)
{
MY_XML_USER_DATA *data= (MY_XML_USER_DATA*)st->user_data;
MY_XML_NODE *nodes= (MY_XML_NODE*) data->pxml->ptr();
uint numnodes= data->pxml->length() / sizeof(MY_XML_NODE);
uint parent= xml_parent_tag(nodes, numnodes, data->level - 1);
MY_XML_NODE node;
data->pos[data->level]= numnodes;
node.level= data->level++;
node.type= st->current_node_type; // TAG or ATTR
node.beg= attr;
node.end= attr + len;
node.parent= parent;
data->pxml->append((const char*) &node, sizeof(MY_XML_NODE));
return MY_XML_OK;
}
/*
Process text node
SYNOPSYS
A call-back function executed when XML parser
is entering into a tag or an attribue textual value.
The value is appended into data->pxml.
RETURN
Currently only MY_XML_OK
*/
static int xml_value(MY_XML_PARSER *st,const char *attr, size_t len)
{
MY_XML_USER_DATA *data= (MY_XML_USER_DATA*)st->user_data;
MY_XML_NODE *nodes= (MY_XML_NODE*) data->pxml->ptr();
uint numnodes= data->pxml->length() / sizeof(MY_XML_NODE);
uint parent= xml_parent_tag(nodes, numnodes, data->level - 1);
MY_XML_NODE node;
node.level= data->level;
node.type= MY_XML_NODE_TEXT;
node.beg= attr;
node.end= attr + len;
node.parent= parent;
data->pxml->append((const char*) &node, sizeof(MY_XML_NODE));
return MY_XML_OK;
}
/*
Leave a tag or an attribute
SYNOPSYS
A call-back function executed when XML parser
is leaving a tag or an attribue.
Decrements data->level.
RETURN
Currently only MY_XML_OK
*/
static int xml_leave(MY_XML_PARSER *st,const char *attr, size_t len)
{
MY_XML_USER_DATA *data= (MY_XML_USER_DATA*)st->user_data;
DBUG_ASSERT(data->level > 0);
data->level--;
MY_XML_NODE *nodes= (MY_XML_NODE*) data->pxml->ptr();
nodes+= data->pos[data->level];
nodes->tagend= st->cur;
return MY_XML_OK;
}
/*
Parse raw XML
SYNOPSYS
RETURN
Currently pointer to parsed XML on success
0 on parse error
*/
String *Item_xml_str_func::parse_xml(String *raw_xml, String *parsed_xml_buf)
{
MY_XML_PARSER p;
MY_XML_USER_DATA user_data;
int rc;
parsed_xml_buf->length(0);
/* Prepare XML parser */
my_xml_parser_create(&p);
p.flags= MY_XML_FLAG_RELATIVE_NAMES | MY_XML_FLAG_SKIP_TEXT_NORMALIZATION;
user_data.level= 0;
user_data.pxml= parsed_xml_buf;
my_xml_set_enter_handler(&p, xml_enter);
my_xml_set_value_handler(&p, xml_value);
my_xml_set_leave_handler(&p, xml_leave);
my_xml_set_user_data(&p, (void*) &user_data);
/* Add root node */
p.current_node_type= MY_XML_NODE_TAG;
xml_enter(&p, raw_xml->ptr(), 0);
/* Execute XML parser */
if ((rc= my_xml_parse(&p, raw_xml->ptr(), raw_xml->length())) != MY_XML_OK)
{
char buf[128];
my_snprintf(buf, sizeof(buf)-1, "parse error at line %d pos %lu: %s",
my_xml_error_lineno(&p) + 1,
my_xml_error_pos(&p) + 1,
my_xml_error_string(&p));
push_warning_printf(current_thd, MYSQL_ERROR::WARN_LEVEL_WARN,
ER_WRONG_VALUE,
ER(ER_WRONG_VALUE), "XML", buf);
}
my_xml_parser_free(&p);
return rc == MY_XML_OK ? parsed_xml_buf : 0;
}
String *Item_func_xml_extractvalue::val_str(String *str)
{
String *res;
if (!nodeset_func ||
!(res= args[0]->val_str(str)) ||
!parse_xml(res, &pxml))
{
null_value= 1;
return 0;
}
res= nodeset_func->val_str(&tmp_value);
return res;
}
String *Item_func_xml_update::val_str(String *str)
{
String *res, *nodeset, *rep;
if (!nodeset_func ||
!(res= args[0]->val_str(str)) ||
!(rep= args[2]->val_str(&tmp_value3)) ||
!parse_xml(res, &pxml) ||
!(nodeset= nodeset_func->val_nodeset(&tmp_value2)))
{
null_value= 1;
return 0;
}
MY_XML_NODE *nodebeg= (MY_XML_NODE*) pxml.ptr();
MY_XPATH_FLT *fltbeg= (MY_XPATH_FLT*) nodeset->ptr();
MY_XPATH_FLT *fltend= (MY_XPATH_FLT*) (nodeset->ptr() + nodeset->length());
/* Allow replacing of one tag only */
if (fltend - fltbeg != 1)
{
/* TODO: perhaps add a warning that more than one tag selected */
return res;
}
nodebeg+= fltbeg->num;
tmp_value.length(0);
tmp_value.set_charset(collation.collation);
uint offs= nodebeg->type == MY_XML_NODE_TAG ? 1 : 0;
tmp_value.append(res->ptr(), nodebeg->beg - res->ptr() - offs);
tmp_value.append(rep->ptr(), rep->length());
const char *end= nodebeg->tagend + offs;
tmp_value.append(end, res->ptr() + res->length() - end);
return &tmp_value;
}