php処理xmlドキュメントの解析関数
67185 ワード
php xml ， xml 。 。 xml ， xml 。 xml 。
， ，
<?
php
$file
=
"
xmltest.xml
"
;
//
function
trustedFile(
$file
) {
//
only trust local files owned by ourselves
if
(
!
eregi
(
"
^([a-z]+)://
"
,
$file
)
&&
fileowner
(
$file
)
==
getmyuid
()) {
return
true
;
}
return
false
;
}
//
。 。
// $attribs
function
startElement(
$parser
,
$name
,
$attribs
=
array
() ) {
print
"
<<font color=\
"
#
0000cc\">$name</font>";
if
(
sizeof
(
$attribs
)) {
while
(
list
(
$k
,
$v
)
=
each
(
$attribs
)) {
print
"
<font color=\
"
#
009900\">$k</font>=\"<font
color
=
\
"
#990000\
"
>
$v
</
font
>
\
""
;
}
}
print
"
>
"
;
}
//
function
endElement(
$parser
,
$name
) {
print
"
</<font color=\
"
#
0000cc\">$name</font>>";
}
//
function
characterData(
$parser
,
$data
) {
print
"
<b>
$data
</b>
"
;
}
//
（PI）
function
PIHandler(
$parser
,
$target
,
$data
) {
switch
(
strtolower
(
$target
)) {
case
"
php
"
:
global
$parser_file
;
//
If the parsed document is "trusted", we say it is safe
// to execute PHP code inside it. If not, display the code
// instead.
if
(trustedFile(
$parser_file
[
$parser
])) {
eval
(
$data
);
}
else
{
printf
(
"
Untrusted PHP code: <i>%s</i>
"
,
htmlspecialchars
(
$data
));
}
break
;
}
}
//
function
defaultHandler(
$parser
,
$data
) {
if
(
substr
(
$data
,
0
,
1
)
==
"
&
"
&&
substr
(
$data
,
-
1
,
1
)
==
"
;
"
) {
//
， 。
printf
(
'
<font color="#aa00aa">%s</font>
'
,
htmlspecialchars
(
$data
));
}
else
{
printf
(
'
<font size="-1">%s</font>
'
,
htmlspecialchars
(
$data
));
}
}
//
function
externalEntityRefHandler(
$parser
,
$openEntityNames
,
$base
,
$systemId
,
$publicId
) {
if
(
$systemId
) {
if
(
!
list
(
$parser
,
$fp
)
=
new_xml_parser(
$systemId
)) {
printf
(
"
Could not open entity %s at %s
"
,
$openEntityNames
,
$systemId
);
return
false
;
}
while
(
$data
=
fread
(
$fp
,
4096
)) {
if
(
!
xml_parse
(
$parser
,
$data
,
feof
(
$fp
))) {
printf
(
"
XML error: %s at line %d while parsing entity %s
"
,
xml_error_string
(
xml_get_error_code
(
$parser
))
,
xml_get_current_line_number
(
$parser
)
,
$openEntityNames
);
xml_parser_free
(
$parser
);
return
false
;
}
}
xml_parser_free
(
$parser
);
return
true
;
}
return
false
;
}
//
xml 。
function
new_xml_parser(
$file
) {
global
$parser_file
;
$xml_parser
=
xml_parser_create
();
//
XML ， 。
xml_parser_set_option
(
$xml_parser
,
XML_OPTION_CASE_FOLDING
,
1
);
//
，
xml_set_element_handler
(
$xml_parser
,
"
startElement
"
,
"
endElement
"
);
//
，bool
xml_set_character_data_handler
(
$xml_parser
,
"
characterData
"
);
//
,bool
xml_set_processing_instruction_handler
(
$xml_parser
,
"
PIHandler
"
);
//
（PI）
xml_set_default_handler
(
$xml_parser
,
"
defaultHandler
"
);
//
xml_set_external_entity_ref_handler
(
$xml_parser
,
"
externalEntityRefHandler
"
);
//
if
(
!
(
$fp
=
@
fopen
(
$file
,
"
r
"
))) {
return
false
;
}
if
(
!
is_array
(
$parser_file
)) {
settype
(
$parser_file
,
"
array
"
);
//
array
}
$parser_file
[
$xml_parser
]
=
$file
;
//
？ ？( )
// echo "<font color=red >parser = ";
// print_r($parser_file);
// echo "<br>$xml_parser";
// echo "</font>";
return
array
(
$xml_parser
,
$fp
);
//
}
if
(
!
(
list
(
$xml_parser
,
$fp
)
=
new_xml_parser(
$file
))) {
die
(
"
could not open XML input
"
);
}
print
"
<pre>
"
;
while
(
$data
=
fread
(
$fp
,
4096
)) {
if
(
!
xml_parse
(
$xml_parser
,
$data
,
feof
(
$fp
))) {
//
。 if ， 。
die
(
sprintf
(
"
XML error: %s at line %d
"
,
xml_error_string
(
xml_get_error_code
(
$xml_parser
))
,
xml_get_current_line_number
(
$xml_parser
)));
}
}
print
"
</pre>
"
;
print
"
parse complete
"
;
xml_parser_free
(
$xml_parser
);
?>
xmltest
.
xml
<?
xml version
=
"
1.0
"
encoding
=
"
UTF-8
"
?>
<!--
xml ，
-->
<
chapter
>
<
TITLE
>
Title
</
TITLE
>
<
para
>
<
informaltable
>
<
tgroup cols
=
"
3
"
>
<
tbody
>
<
row
><
entry
>
a1
</
entry
><
entry morerows
=
"
1
"
>
b1
</
entry
><
entry
>
c1
</
entry
></
row
>
<
row
><
entry
>
a2
</
entry
><
entry
>
c2
</
entry
></
row
>
<
row
><
entry
>
a3
</
entry
><
entry
>
b3
</
entry
><
entry
>
c3
</
entry
></
row
>
</
tbody
>
</
tgroup
>
</
informaltable
>
</
para
>
<
section id
=
"
about
"
>
<
title
>
About this Document
</
title
>
<
para
>
<!--
this is a comment
-->
<?
php
print
'
Hi! This is PHP version
'
.
phpversion
();
?>
</
para
>
</
section
>
</
chapter
>
xml php 。
<?
php
class
AminoAcid {
var
$name
;
//
aa name
var
$symbol
;
//
three letter symbol
var
$code
;
//
one letter code
var
$type
;
//
hydrophobic, charged or neutral
function
AminoAcid (
$aa
) {
foreach
(
$aa
as
$k
=>
$v
)
$this
->
$k
=
$aa
[
$k
];
}
}
function
readDatabase(
$filename
) {
//
read the xml database of aminoacids
$data
=
implode
(
""
,
file
(
$filename
));
//
， ， $data.
$parser
=
xml_parser_create
();
xml_parser_set_option
(
$parser
,
XML_OPTION_CASE_FOLDING
,
0
);
//
xml_parser_set_option
(
$parser
,
XML_OPTION_SKIP_WHITE
,
1
);
xml_parse_into_struct
(
$parser
,
$data
,
$values
,
$tags
);
//
XML ， XML ，
//$tags $values 。 。
xml_parser_free
(
$parser
);
//
loop through the structures
// ( xml ， 。
foreach
(
$tags
as
$key
=>
$val
) {
if
(
$key
==
"
molecule
"
) {
$molranges
=
$val
;
//
each contiguous pair of array entries are the
// lower and upper range for each molecule definition
for
(
$i
=
0
;
$i
<
count
(
$molranges
);
$i
+=
2
) {
$offset
=
$molranges
[
$i
]
+
1
;
$len
=
$molranges
[
$i
+
1
]
-
$offset
;
$tdb
[]
=
parseMol(
array_slice
(
$values
,
$offset
,
$len
));
}
}
else
{
continue
;
}
}
//
echo "<font color=red>values is:";
// print_r($values);
// echo "</font>";
return
array
(
$tdb
,
$values
);
}
function
parseMol(
$mvalues
) {
for
(
$i
=
0
;
$i
<
count
(
$mvalues
);
$i
++
)
$mol
[
$mvalues
[
$i
][
"
tag
"
]]
=
$mvalues
[
$i
][
"
value
"
];
//
echo "<font color=blue> after parsemol :";
// print_r($mol);
// echo "</font>";
return
new
AminoAcid(
$mol
);
}
$db
=
readDatabase(
"
moldb.xml
"
);
echo
"
** Database of AminoAcid objects:
"
;
//
echo "<font color=purple> readdatabase :";
print_r
(
$db
[
0
]);
//
echo "</font>";
$s
=
parseMol(
$db
[
1
]);
?>
moldb
.
xml
<?
xml version
=
"
1.0
"
encoding
=
"
UTF-8
"
?>
<
moldb
>
<
molecule
>
<
name
>
Alanine
</
name
>
<
symbol
>
ala
</
symbol
>
<
code
>
A
</
code
>
<
type
>
hydrophobic
</
type
>
</
molecule
>
<
molecule
>
<
name
>
Lysine
</
name
>
<
symbol
>
lys
</
symbol
>
<
code
>
K
</
code
>
<
type
>
charged
</
type
>
</
molecule
>
</
moldb
>