1
Fork 0
mirror of https://git.savannah.gnu.org/git/guile.git synced 2025-04-30 11:50:28 +02:00

xml->sxml argument can be a port or a string

* module/sxml/simple.scm (xml->sxml): Allow the optional arg to be a
  port or a string.
* doc/ref/sxml.texi (Reading and Writing XML): Update docs.
This commit is contained in:
Andy Wingo 2013-01-28 12:01:16 +01:00
parent 1488753a66
commit a14b6e1825
2 changed files with 31 additions and 33 deletions

View file

@ -55,13 +55,14 @@ to text.
(use-modules (sxml simple))
@end example
@deffn {Scheme Procedure} xml->sxml [port] [#:namespaces='()] @
@deffn {Scheme Procedure} xml->sxml [string-or-port] [#:namespaces='()] @
[#:declare-namespaces?=#t] [#:trim-whitespace?=#f] @
[#:entities='()] [#:default-entity-handler=#f]
Use SSAX to parse an XML document into SXML. Takes one optional
argument, @var{port}, which defaults to the current input port. Returns
the resulting SXML document, and leaves @var{port} pointing at the next
available character in the port.
argument, @var{string-or-port}, which defaults to the current input
port. Returns the resulting SXML document. If @var{string-or-port} is
a port, it will be left pointing at the next available character in the
port.
@end deffn
As is normal in SXML, XML elements parse as tagged lists. Attributes,
@ -71,13 +72,13 @@ This tag will contain the root element of the XML, but also any prior
processing instructions.
@example
(xml->sxml (open-input-string "<foo/>"))
(xml->sxml "<foo/>")
@result{} (*TOP* (foo))
(xml->sxml (open-input-string "<foo>text</foo>"))
(xml->sxml "<foo>text</foo>")
@result{} (*TOP* (foo "text"))
(xml->sxml (open-input-string "<foo kind=\"bar\">text</foo>"))
(xml->sxml "<foo kind=\"bar\">text</foo>")
@result{} (*TOP* (foo (@@ (kind "bar")) "text"))
(xml->sxml (open-input-string "<?xml version=\"1.0\"?><foo/>"))
(xml->sxml "<?xml version=\"1.0\"?><foo/>")
@result{} (*TOP* (*PI* xml "version=\"1.0\"") (foo))
@end example
@ -88,18 +89,12 @@ for certain namespaces with the @code{#:namespaces} keyword argument to
@code{xml->sxml}.
@example
(xml->sxml
(open-input-string
"<foo xmlns=\"http://example.org/ns1\">text</foo>"))
(xml->sxml "<foo xmlns=\"http://example.org/ns1\">text</foo>")
@result{} (*TOP* (http://example.org/ns1:foo "text"))
(xml->sxml
(open-input-string
"<foo xmlns=\"http://example.org/ns1\">text</foo>")
(xml->sxml "<foo xmlns=\"http://example.org/ns1\">text</foo>"
#:namespaces '((ns1 . "http://example.org/ns1")))
@result{} (*TOP* (ns1:foo "text"))
(xml->sxml
(open-input-string
"<foo xmlns:bar=\"http://example.org/ns2\"><bar:baz/></foo>")
(xml->sxml "<foo xmlns:bar=\"http://example.org/ns2\"><bar:baz/></foo>"
#:namespaces '((ns2 . "http://example.org/ns2")))
@result{} (*TOP* (foo (ns2:baz)))
@end example
@ -109,10 +104,10 @@ user-given @code{#:namespaces} to be treated as if they were declared on
the root element.
@example
(xml->sxml (open-input-string "<foo><ns2:baz/></foo>")
(xml->sxml "<foo><ns2:baz/></foo>"
#:namespaces '((ns2 . "http://example.org/ns2")))
@result{} error: undeclared namespace: `bar'
(xml->sxml (open-input-string "<foo><ns2:baz/></foo>")
(xml->sxml "<foo><ns2:baz/></foo>"
#:namespaces '((ns2 . "http://example.org/ns2"))
#:declare-namespaces? #t)
@result{} (*TOP* (foo (ns2:baz)))
@ -124,11 +119,9 @@ whitespace in front, behind and between elements, treating it as
``unsignificant''. Whitespace in text fragments is left alone.
@example
(xml->sxml (open-input-string
"<foo>\n<bar> Alfie the parrot! </bar>\n</foo>"))
(xml->sxml "<foo>\n<bar> Alfie the parrot! </bar>\n</foo>")
@result{} (*TOP* (foo "\n" (bar " Alfie the parrot! ") "\n")
(xml->sxml (open-input-string
"<foo>\n<bar> Alfie the parrot! </bar>\n</foo>")
(xml->sxml "<foo>\n<bar> Alfie the parrot! </bar>\n</foo>"
#:trim-whitespace? #t)
@result{} (*TOP* (foo (bar " Alfie the parrot! "))
@end example
@ -141,16 +134,16 @@ default, only the standard @code{&lt;}, @code{&gt;}, @code{&amp;},
numeric character entities.
@example
(xml->sxml (open-input-string "<foo>&amp;</foo>"))
(xml->sxml "<foo>&amp;</foo>")
@result{} (*TOP* (foo "&"))
(xml->sxml (open-input-string "<foo>&nbsp;</foo>"))
(xml->sxml "<foo>&nbsp;</foo>")
@result{} error: undefined entity: nbsp
(xml->sxml (open-input-string "<foo>&#xA0;</foo>"))
(xml->sxml "<foo>&#xA0;</foo>")
@result{} (*TOP* (foo "\xa0"))
(xml->sxml (open-input-string "<foo>&nbsp;</foo>")
(xml->sxml "<foo>&nbsp;</foo>"
#:entities '((nbsp . "\xa0")))
@result{} (*TOP* (foo "\xa0"))
(xml->sxml (open-input-string "<foo>&nbsp; &foo;</foo>")
(xml->sxml "<foo>&nbsp; &foo;</foo>"
#:default-entity-handler
(lambda (port name)
(case name

View file

@ -76,14 +76,15 @@
;;
;; * Parse external DTDs
;;
(define* (xml->sxml #:optional (port (current-input-port)) #:key
(define* (xml->sxml #:optional (string-or-port (current-input-port)) #:key
(namespaces '())
(declare-namespaces? #t)
(trim-whitespace? #f)
(entities '())
(default-entity-handler #f))
"Use SSAX to parse an XML document into SXML. Takes one optional
argument, @var{port}, which defaults to the current input port."
argument, @var{string-or-port}, which defaults to the current input
port."
;; NAMESPACES: alist of PREFIX -> URI. Specifies the symbol prefix
;; that the user wants on elements of a given namespace in the
;; resulting SXML, regardless of the abbreviated namespaces defined in
@ -178,7 +179,11 @@ argument, @var{port}, which defaults to the current input port."
(list '*PI* pi-tag (ssax:read-pi-body-as-string port))
seed))))))
`(*TOP* ,@(reverse (parser port '()))))
(let* ((port (if (string? string-or-port)
(open-input-string string-or-port)
string-or-port))
(elements (reverse (parser port '()))))
`(*TOP* ,@elements)))
(define check-name
(let ((*good-cache* (make-hash-table)))