From a4e680e949795e07be981a2663eb9bdc3d3028b1 Mon Sep 17 00:00:00 2001 From: dlichteblau Date: Sat, 25 Jun 2005 13:56:50 +0000 Subject: [PATCH] new release --- README.html | 931 +++--------------------------------------- cxml.asd | 1 - doc/cxml.css | 42 ++ doc/installation.html | 164 ++++++++ doc/using.html | 705 ++++++++++++++++++++++++++++++++ runes/runes.lisp | 15 +- test/domtest.lisp | 42 +- 7 files changed, 998 insertions(+), 902 deletions(-) create mode 100644 doc/cxml.css create mode 100644 doc/installation.html create mode 100644 doc/using.html diff --git a/README.html b/README.html index ac3588a..7ff881f 100644 --- a/README.html +++ b/README.html @@ -3,33 +3,41 @@ Closure XML - + +
+

+ CXML Homepage +

+ +
+

Closure XML Parser

An XML parser written in Common Lisp.

@@ -47,14 +55,27 @@ (SAX layer; namespace support)
  • - David Lichteblau for David Lichteblau for knowledgeTools (conversion into an independent package; DOM bug fixing; validation) and headcraft - (most september 2004 changes) and privately (changes since then). + (most september/october 2004 changes) and privately (changes + since then).
    • +

    + CXML currently implements a namespace-aware, validating SAX-like + XML 1.0 + parser as well as the DOM Level 1 Core + interfaces. +

    + +

    + CXML is licensed under (L)LGPL. +

    +

    Send bug reports to cxml-devel@common-lisp.net @@ -63,59 +84,16 @@ information).

    -

    Download

    - -

    - (David's tla archive is out of date.) -

    - -

    Contents

    - -

    Recent Changes

    -

    patch-xyz (200-mm-dd)

    +

    rel-2005-06-25

    patch-357 (2004-10-10)

    -     -

    CXML Modules

    -

    CXML provides three packages:

    -     - - -

    Installation

    -

    - CXML should be portable to all Common Lisp implementations - supporting gray streams.  Currently assumed to work are: -

    - -

    - Incomplete port: -

    - - -

    - Optional configuration (skip this unless you know better): CXML - has full Unicode code support -- even on Lisps without Unicode - strings. On non-unicode aware Lisps, DOMString is - implemented as an array of character codes. CXML will auto-detect - at compile-time which string representation to use. To override - the auto-detection, you can set one of the features - :rune-is-character and :rune-is-octet before - loading cxml.asd. (fixme: feature - :rune-is-octet is of course misnamed, since it uses 16bit - runes, not 8bit runes. It will probably be renamed - to :rune-is-integer at some point.) -

    - -

    - ASDF is used for - compilation. The following instructions assume that ASDF has - already been loaded. -

    - -

    - Prerequisites. - CXML needs the puri library. -

    - -

    - Compiling and loading CXML. - Register the .asd file, e.g. by symlinking it: -

    - 
    $ ln -sf `pwd`/cxml.asd /path/to/your/registry/
    -

    Then compile CXML using:

    - 
    * (asdf:operate 'asdf:load-op :cxml)
    - -

    - You can then try the quick-start example. -

    - - -

    Tests

    -

    Check out the XML and DOM testsuites:

    - 
    $ export CVSROOT=:pserver:anonymous@dev.w3.org:/sources/public
-$ cvs login    # password is "anonymous"
-$ cvs co 2001/XML-Test-Suite/xmlconf
-$ cvs co -D '2005-05-06 23:00' 2001/DOM-Test-Suite
-$ cd 2001/DOM-Test-Suite && ant dom1-dtd
    -

    - Omit -D to get the latest version, which may not work - with cxml yet. The ant step is necessary to run the DOM - tests. -

    -

    Usage and expected output:

    - 
    * (xmlconf:run-all-tests "/path/to/2001/XML-Test-Suite/xmlconf/")
-0/556 tests failed; 1606 tests were skipped
-* (domtest:run-all-tests "/path/to/2001/DOM-Test-Suite/")
-0/450 tests failed; 71 tests were skipped
    - -

    - fixme: Add an explanation of xml/sax-tests here. -

    - -

    - fixme My parser does not understand the current testsuite - anymore.  To fix this problem, revert the affected files - manually after check-out: -

    - - 
    $ cd 2001/XML-Test-Suite/xmlconf/
-xmltest$ patch -p0 -R </path/to/cxml/test/xmlconf-base.diff
    - -

    - The log message for the changes reads "Removed unnecessary - xml:base attribute".  If I understand correctly, only - DOM 3 parsers provide the baseURI attribute necessary for - understanding xmlconf.xml now.  We don't have that - yet. -

    - + -     -

    Using CXML

    - -     -

    Quick-Start Example

    - -

    - Make sure to install and load cxml first. -

    - -

    Create a test file called example.xml:

    - 
    * (with-open-file (s "example.xml" :direction :output)
-    (write-string "<test a='b'><child/></test>" s))
    - -

    Parse example.xml into a DOM tree (read - more):

    - 
    * (cxml:parse-file "example.xml" (dom:make-dom-builder))
-#<DOM-IMPL::DOCUMENT @ #x72206172>
-;; save result for later:
-* (defparameter *example* *)
-*EXAMPLE*
    - -

    Inspect the DOM tree (read more):

    - 
    * (dom:document-element *example*)
-#<DOM-IMPL::ELEMENT test @ #x722b6ba2>
-* (dom:tag-name (dom:document-element *example*))
-"test"
-* (dom:child-nodes (dom:document-element *example*))
-#(#<DOM-IMPL::ELEMENT child @ #x722b6d8a>)
-* (dom:get-attribute (dom:document-element *example*) "a")
-"b"
    - -

    Serialize the DOM document back into a stream (read more):

    - 
    (cxml:unparse-document *example* *standard-output*)
-<test a="b"><child></child></test>
    - -

    As an alternative to DOM, parse into xmls-compatible list - structure (read more):

    - 
    * (cxml:parse-file "example.xml" (cxml-xmls:make-xmls-builder))
-("test" (("a" "b")) ("child" NIL))
    - - -

    Parsing and Validating

    -

    -

    Function CXML:PARSE-FILE (pathname handler &key ...)
    -
    Function CXML:PARSE-STREAM (stream handler &key ...)
    -
    Function CXML:PARSE-OCTETS (octets handler &key ...)
    - Parse an XML document.  - Return values from this function depend on the SAX handler used.
    - Arguments: -

    - -

    - Common keyword arguments: -

    - - -

    -

    Function CXML:PARSE-DTD-FILE (pathname)
    -
    Function CXML:PARSE-DTD-STREAM (stream)
    - Parse     declarations - from a stand-alone file and return an object representing the DTD, - suitable as an argument to validate. -

    - - -

    -

    Function CXML:MAKE-EXTID (publicid systemid)
    - Create an object representing the External ID composed - of the specified Public ID, a rod or nil, and System ID - (an URI object). -

    - -

    -

    Function DOM:MAKE-DOM-BUILDER ()
    - Create a SAX handler which builds a DOM document.  Example: -

    - 
    (cxml:parse-file "test.xml" (dom:make-dom-builder))
    - - -

    Serialization

    -

    -

    Function CXML:UNPARSE-DOCUMENT (document stream &rest keys)
    -
    Function CXML:UNPARSE-DOCUMENT-TO-OCTETS (document &rest keys) => vector
    - Serialize a DOM document object. -

    - -

    Keyword arguments:

    - -

    - The following canonical values are allowed: -

    -     -

    - With an indentation level, pretty-print the XML by - inserting additional whitespace.  Note that indentation - changes the document model and should only be used if whitespace - does not matter to the application. -

    -

    - unparse-document-to-octets returns an (unsigned-byte - 8) array, whereas unparse-document writes - characters.  unparse-document is useful together - with with-output-to-string.  However, note that the - resulting document in both cases is UTF-8 encoded, so the - characters written by unparse-document are really UTF-8 - bytes encoded as characters. -

    - -

    -

    Function CXML:MAKE-CHARACTER-STREAM-SINK (stream &rest keys) => sink
    -
    Function CXML:MAKE-OCTET-VECTOR-SINK (&rest keys) => sink
    - Return a handle suitable for event-based XML serialization. -

    -

    - These function provide the low-level mechanism used by the DOM - serialization functions. To serialize a document without building - its DOM tree first, create a sink handle and call SAX functions on that - handle. sax:end-document returns the serialized form of - the document described by the SAX events. -

    - -

    -

    Macro CXML:WITH-XML-OUTPUT (sink &body body) => vector
    -
    Macro CXML:WITH-ELEMENT (qname &body body) => result
    -
    Function CXML:ATTRIBUTE (name value) => value
    -
    Function CXML:TEXT (data) => data
    -
    Function CXML:CDATA (data) => data
    - Convenience syntax for event-based serialization. -

    -

    - Example: -

    - 
    (with-xml-output (make-octet-stream-sink stream :indentation 2 :canonical nil)
-  (with-element "foo"
-    (attribute "xyz" "abc")
-    (with-element "bar"
-      (attribute "blub" "bla"))
-    (text "Hi there.")))
    -

    - Prints this to stream, which must be an - (unsigned-byte 8) stream: -

    - 
    <foo xyz="abc">
-  <bar blub="bla"></bar>
-  Hi there.
-</foo>
    -

    - (Note that these functions accept both strings and rods, so we - could write "foo" instead of #"foo" above.) -

    - -

    -

    Macro XHTML-GENERATOR:WITH-XHTML (sink &rest forms)
    -
    Macro XHTML-GENERATOR:WRITE-DOCTYPE (sink)
    - Macro with-xhtml is a modified version of - Franz' htmlgen works as a SAX driver for XHTML. - It aims to be a plug-in replacement for the html macro. -

    -

    - xhtmlgen is included as contrib/xhtmlgen.lisp in - the cxml distribution. Example: -

    - 
    (let ((sink (cxml:make-character-stream-sink *standard-output*)))
-  (sax:start-document sink)
-  (xhtml-generator:write-doctype sink)
-  (xhtml-generator:with-html sink
-    (:html
-     (:head
-      (:title "Titel"))
-     (:body
-      ((:p "style" "font-weight: bold")
-       "Inhalt")
-      (:ul
-       (:li "Eins")
-       (:li "Zwei")
-       (:li "Drei")))))
-  (sax:end-document sink))
    - - -

    Miscellaneous Utility Functions

    -

    -

    Function CXML:MAKE-VALIDATOR (dtd root)
    - Create a SAX handler which validates against a DTD instance.  - The document's root element must be named root.  - Used with dom:map-document, this validates a document - object as if by re-reading it with a validating parser, except - that declarations recorded in the document instance are completely - ignored.
    - Example: -

    - 
    (let ((d (parse-file "~/test.xml" (dom:make-dom-builder)))
-      (x (parse-dtd-file "~/test.dtd")))
-  (dom:map-document (cxml:make-validator x #"foo") d))
    - -

    -

    Function DOM:MAP-DOCUMENT (handler document &key include-xmlns-attributes include-default-values)
    - Traverse a DOM document and call SAX functions as if an XML - representation of the document were processed by a SAX parser. -

    - -

    -

    Class CXML:SAX-PROXY ()
    -
    Accessor CXML:PROXY-CHAINED-HANDLER
    - sax-proxy is a SAX handler which passes all events it - receives on to a user-defined second handler, which defaults - to nil. Use sax-proxy to modify the events a - SAX handler receives by defining your own subclass - of sax-proxy. Setting the chained handler to the target - handler, and define methods on your handler class for the events - to be modified. All other events will pass through to the chained - handler unmodified. -

    - -     -

    XMLS Compatibility

    -

    - Like other XML parsers written in Lisp, CXML can work with - documents represented as list structures. The specific model - implemented by cxml is compatible with the xmls parser. Xmls - list structures are a simpler and faster alternative to full DOM - document trees. They also serve as an example showing how to - implement user-defined document models as an independent layer - over the the base parser (c.f. xml/xmls-compat.lisp in - the cxml distribution). However, note that the list structures do - not include all information available in DOM documents and are - sometimes more difficult to work wth since many DOM functions - cannot be implemented on them. -

    -

    -

    Function CXML-XMLS:MAKE-XMLS-BUILDER (&key include-default-values)
    - Create a SAX handler which builds XMLS list structures.  - If include-default-values is true, default values for - attributes declared in a DTD are included as attributes in the - xmls output. include-default-values is true by default - and can be set to nil to suppress inclusion of default - values. -

    -

    - Example: -

    - 
    (cxml:parse-file "test.xml" (cxml-xmls:make-xmls-builder))
    -

    -

    Function CXML-XMLS:MAP-NODE (handler node &key include-xmlns-attributes)
    - Traverse an XMLS document/node and call SAX functions as if an XML - representation of the document were processed by a SAX parser. -

    -

    - Use this function to serialize XMLS data. For example, we could - define a replacement for xmls:write-xml like this: -

    - 
    (defun write-xml (stream node &key indent)
-  (let ((sink (cxml:make-character-stream-sink
-               stream :canonical nil :indentation indent)))
-    (cxml-xmls:map-node sink node)))
    -

    -

    Function CXML-XMLS:MAKE-NODE (&key name ns attrs - children) => xmls node
    - Build a list node of the form - (name ((name value)*) child*). -

    -

    - The node list's car can also be a cons of local name - and namespace prefix ns. - fixme: It is unclear to me how namespaces are meant to - work in xmls, since xmls documentation differs from how xmls - actually works in current releases. Usually applications need to - know both the namespace prefix and the namespace URI. We - currently follow the xmls implementation and use the - namespace prefix instead of following its documentation which - shows the URI. We do not follow xmls in munging xmlns attribute - values. Attributes themselves have namespaces and it is not clear - to me how that works in xmls. -

    -

    -

    Accessor CXML-XMLS:NODE-NAME (node)
    -
    Accessor CXML-XMLS:NODE-NS (node)
    -
    Accessor CXML-XMLS:NODE-ATTRS (node)
    -
    Accessor CXML-XMLS:NODE-CHILDREN (node)
    - Accessors for xmls node data. -

    -

    -

    - - -

    Dealing with Rods

    -

    - As explained above, the XML parser handles character encoding and - uses 16bit strings internally. Instead of using characters and strings - it uses runes and rods. This is seen as a - feature, but can be inconvenient. -

    - -

    - Note that the recoder approach does not work with the DOM - builder, since DOM is specified to use UTF-16. -

    -

    -

    Function CXML:MAKE-RECODER (chained-handler &optional recoder-fn)
    - Return a SAX handler which passes all events on to - chained-handler after converting all strings and rods - using recoder-fn, a function of one argument which - defaults to runes:rod-string. -

    -

    - Example. In a Lisp which ordinarily would use octet vector rods: -

    - 
    CL-USER(14): (cxml:parse-string "<test/>" (cxml-xmls:make-xmls-builder))
-(#(116 101 115 116) NIL)
    -

    - Use a SAX recoder to get strings instead:: -

    - 
    CL-USER(17): (parse-string "<test/>" (cxml:make-recoder (cxml-xmls:make-xmls-builder)))
-("test" NIL)
    - -     -

    Caching of DTD Objects

    -

    - To avoid spending time parsing the same DTD over and over again, - CXML can cache DTD objects. The parser consults - cxml:*dtd-cache* whenever it is looking for an external - subset in a document which does not have an internal subset and - uses the cached DTD instance if one is present in the cache for - the System ID in question. -

    -

    - Note that DTDs do not expire from the cache automatically. - (Future versions of CXML might introduce automatic checks for - outdated DTDs.) -

    -

    -

    Variable CXML:*DTD-CACHE*
    - The DTD cache object consulted by the parser when it needs a DTD. -

    -

    -

    Function CXML:MAKE-DTD-CACHE ()
    - Return a new, empty DTD cache object. -

    -

    -

    Variable CXML:*CACHE-ALL-DTDS*
    - If true, instructs the parser to enter all DTDs that could have - been cached into *dtd-cache* if they were not cached - already. Defaults to nil. -

    -

    -

    Reader CXML:GETDTD (uri dtd-cache)
    - Return a cached instance of the DTD at uri, if present in - the cache, or nil. -

    -

    -

    Writer CXML:GETDTD (uri dtd-cache)
    - Enter a new value for uri into dtd-cache. -

    -

    -

    Function CXML:REMDTD (uri dtd-cache)
    - Ensure that no DTD is recorded for uri in the cache and - return true if such a DTD was present. -

    -

    -

    Function CXML:CLEAR-DTD-CACHE (dtd-cache)
    - Remove all entries from dtd-cache. -

    -

    - fixme: thread-safety -

    - -     -

    XML Catalogs

    -

    - External entities (for example, DTDs) are referred to using their - Public and System IDs. Usually the System ID, a URI, is used to - locate the entity. CXML itself handles only file://-URIs, but - many System IDs in practical use are http://-URIs. There are two - different mechanims applications can use to allow CXML to locate - entities using arbitrary Public ID or System ID: -

    -     -

    - This section describes XML Catalogs, the second solution. CXML - implements Oasis - XML Catalogs. -

    -

    -

    Variable CXML:*CATALOG*
    - The XML Catalog object consulted by the parser before trying to - open an entity. Initially nil. -

    -

    -

    Variable CXML:*PREFER*
    - The default "prefer" mode from the Catalog specification, one - of :public or :system. Defaults - to :public. -

    -

    -

    Function CXML:MAKE-CATALOG (&optional uris)
    - Return a catalog object for the catalog files specified. -

    -

    -

    Function CXML:RESOLVE-URI (uri catalog)
    - Look up uri in catalog and return the - resulting URI, or nil if no match was found. -

    -

    -

    Function CXML:RESOLVE-EXTID (publicid systemid catalog)
    - Look up the External ID (publicid, systemid) - in catalog and return the resulting URI, or nil - if no match was found. -

    -

    - Example: -

    - 
    * (setf cxml:*catalog* nil)
-* (cxml:parse-file "test.xhtml" nil)
-=> Error: URI scheme :HTTP not supported
-
-* (setf cxml:*catalog* (cxml:make-catalog))
-* (cxml:parse-file "test.xhtml" nil)
-;; no error!
-NIL
    -

    - Note that parsed catalog files are cached in the catalog object. - Catalog files cached do not expire automatically. To ensure that - all catalog files are parsed again, create a new catalog object. -

    - - -

    SAX Interface

    -

    - A SAX handler is an arbitrary objects that implements some of the - generic functions in the SAX package.  Note that no default - handler class is necessary, because all generic functions have default - methods which do nothing.  SAX functions are: -

    Function SAX:START-DOCUMENT (handler)
    -
    Function SAX:END-DOCUMENT (handler)
    -
    -
    Function SAX:START-ELEMENT (handler namespace-uri local-name qname attributes)
    -
    Function SAX:END-ELEMENT (handler namespace-uri local-name qname)
    -
    Function SAX:START-PREFIX-MAPPING (handler prefix uri)
    -
    Function SAX:END-PREFIX-MAPPING (handler prefix)
    -
    Function SAX:PROCESSING-INSTRUCTION (handler target data)
    -
    Function SAX:COMMENT (handler data)
    -
    Function SAX:START-CDATA (handler)
    -
    Function SAX:END-CDATA (handler)
    -
    Function SAX:CHARACTERS (handler data)
    -
    -
    Function SAX:START-DTD (handler name public-id system-id)
    -
    Function SAX:END-DTD (handler)
    -
    Function SAX:UNPARSED-ENTITY-DECLARATION (handler name public-id system-id notation-name)
    -
    Function SAX:EXTERNAL-ENTITY-DECLARATION (handler kind name public-id system-id)
    -
    Function SAX:INTERNAL-ENTITY-DECLARATION (handler kind name value)
    -
    Function SAX:NOTATION-DECLARATION (handler name public-id system-id)
    -
    Function SAX:ELEMENT-DECLARATION (handler name model)
    -
    Function SAX:ATTRIBUTE-DECLARATION (handler ename aname type default)
    -
    -
    Accessor SAX:ATTRIBUTE-PREFIX (attribute)
    -
    Accessor SAX:ATTRIBUTE-NAMESPACE-URI (attribute)
    -
    Accessor SAX:ATTRIBUTE-LOCAL-NAME (attribute)
    -
    Accessor SAX:ATTRIBUTE-VALUE (attribute)
    -
    Accessor SAX:ATTRIBUTE-QNAME (attribute)
    -
    Accessor SAX:ATTRIBUTE-SPECIFIED-P (attribute)
    -

    -

    - The entity declaration methods are similar to Java SAX - definitions, but parameter entities are distinguished from - general entities not by a % prefix to the name, but by - the kind argument, either :parameter or - :general. -

    -

    - The arguments to sax:element-declaration and - sax:attribute-declaration differ significantly from their - Java counterparts. -

    -

    - fixme: For more information on these functions refer to the docstrings. -

    - - -     -

    DOM Notes

    -

    - CXML implements the DOM Level 1 Core interfaces.  Explaining - DOM is better left to the specification, - so please refer to the official W3C documents for DOM. -

    -

    - However, there is no "standard" DOM mapping for Lisp.  DOM - is specified - in CORBA IDL, but it refrains from using object-oriented IDL - features, allowing for a much more natural Lisp implemenation than - the the ordinary IDL/Lisp mapping would. -

    -

    - Differences between CXML's DOM and the direct IDL/Lisp mapping: -

    - -

    Example:

    - 
    XML(97): (dom:node-type
-          (dom:document-element
-           (cxml:parse-file "~/test.xml" (dom:make-dom-builder))))
-:ELEMENT
    diff --git a/cxml.asd b/cxml.asd index 1e1e4ce..20d256d 100644 --- a/cxml.asd +++ b/cxml.asd @@ -98,7 +98,6 @@ (:file "dom-impl" :depends-on ("package")) (:file "dom-builder" :depends-on ("dom-impl")) (:file "unparse" :depends-on ("package")) - (:file "simple-dom" :depends-on ("package")) (:file "dom-sax" :depends-on ("package"))) :depends-on (:xml)) diff --git a/doc/cxml.css b/doc/cxml.css new file mode 100644 index 0000000..d35d8d6 --- /dev/null +++ b/doc/cxml.css @@ -0,0 +1,42 @@ +div.sidebar { + float: right; + background-color: #eeeeee; + border: 2pt solid black; + margin: 0em 2pt 1em 2em; + min-width: 15%; + padding: 0pt 5pt 5pt 5pt; +} + +div.sidebar ul { + padding: 0pt 0pt 0pt 1em; + margin: 0 0 1em; +} + +body { + color: #000000; + background-color: #ffffff; + margin-right: 0pt; + margin-bottom: 10%; + padding-left: 30px; +} + +h1,h2,h3 { + margin-left: -30px; +} + +pre { + background-color: #eeeeee; + border: solid 1px #d0d0d0; + padding: 1em; + margin-right: 10%; +} + +.def { + background-color: #ddddff; + font-weight: bold; +} + +.nomargin { + margin-bottom: 0; + margin-top: 0; +} diff --git a/doc/installation.html b/doc/installation.html new file mode 100644 index 0000000..365f016 --- /dev/null +++ b/doc/installation.html @@ -0,0 +1,164 @@ + + + + + Closure XML + + + +
    +

    + CXML Homepage +

    + +
    +

    Installation of Closure XML

    + + +

    Download

    +     + + +

    Implementation-specific notes

    +

    + CXML should be portable to all Common Lisp implementations + supporting gray streams. Currently supported are ACL, CLISP, + CMUCL, LispWorks, OpenMCL, and SBCL. +

    +     + + + + +

    Compilation

    +

    + ASDF is used for + compilation. The following instructions assume that ASDF has + already been loaded. +

    + +

    + Prerequisites. + CXML needs the puri library. +

    + +

    + Compiling and loading CXML. + Register the .asd file, e.g. by symlinking it: +

    + 
    $ ln -sf `pwd`/cxml.asd /path/to/your/registry/
    +

    Then compile CXML using:

    + 
    * (asdf:operate 'asdf:load-op :cxml)
    + +

    + You can then try the quick-start example. +

    + + +

    Tests

    +

    Check out the XML and DOM testsuites:

    + 
    $ export CVSROOT=:pserver:anonymous@dev.w3.org:/sources/public
+$ cvs login    # password is "anonymous"
+$ cvs co 2001/XML-Test-Suite/xmlconf
+$ cvs co -D '2005-05-06 23:00' 2001/DOM-Test-Suite
+$ cd 2001/DOM-Test-Suite && ant dom1-dtd
    +

    + Omit -D to get the latest version, which may not work + with cxml yet. The ant step is necessary to run the DOM + tests. +

    +

    Usage and expected output:

    + 
    * (xmlconf:run-all-tests "/path/to/2001/XML-Test-Suite/xmlconf/")
+0/556 tests failed; 1606 tests were skipped
+* (domtest:run-all-tests "/path/to/2001/DOM-Test-Suite/")
+0/449 tests failed; 71 tests were skipped
    + +

    + fixme: Add an explanation of xml/sax-tests here. +

    + +

    + fixme My parser does not understand the current testsuite + anymore.  To fix this problem, revert the affected files + manually after check-out: +

    + + 
    $ cd 2001/XML-Test-Suite/xmlconf/
+xmltest$ patch -p0 -R </path/to/cxml/test/xmlconf-base.diff
    + +

    + The log message for the changes reads "Removed unnecessary + xml:base attribute".  If I understand correctly, only + DOM 3 parsers provide the baseURI attribute necessary for + understanding xmlconf.xml now.  We don't have that + yet. +

    + + diff --git a/doc/using.html b/doc/using.html new file mode 100644 index 0000000..02c7589 --- /dev/null +++ b/doc/using.html @@ -0,0 +1,705 @@ + + + + + Closure XML + + + +
    +

    + CXML Homepage +

    + +
    +

    Using Closure XML

    + + +

    Quick-Start Example

    + +

    + Make sure to install and load cxml first. +

    + +

    Create a test file called example.xml:

    + 
    * (with-open-file (s "example.xml" :direction :output)
+    (write-string "<test a='b'><child/></test>" s))
    + +

    Parse example.xml into a DOM tree (read + more):

    + 
    * (cxml:parse-file "example.xml" (dom:make-dom-builder))
+#<DOM-IMPL::DOCUMENT @ #x72206172>
+;; save result for later:
+* (defparameter *example* *)
+*EXAMPLE*
    + +

    Inspect the DOM tree (read more):

    + 
    * (dom:document-element *example*)
+#<DOM-IMPL::ELEMENT test @ #x722b6ba2>
+* (dom:tag-name (dom:document-element *example*))
+"test"
+* (dom:child-nodes (dom:document-element *example*))
+#(#<DOM-IMPL::ELEMENT child @ #x722b6d8a>)
+* (dom:get-attribute (dom:document-element *example*) "a")
+"b"
    + +

    Serialize the DOM document back into a stream (read more):

    + 
    (cxml:unparse-document *example* *standard-output*)
+<test a="b"><child></child></test>
    + +

    As an alternative to DOM, parse into xmls-compatible list + structure (read more):

    + 
    * (cxml:parse-file "example.xml" (cxml-xmls:make-xmls-builder))
+("test" (("a" "b")) ("child" NIL))
    + + +

    Parsing and Validating

    +

    +

    Function CXML:PARSE-FILE (pathname handler &key ...)
    +
    Function CXML:PARSE-STREAM (stream handler &key ...)
    +
    Function CXML:PARSE-OCTETS (octets handler &key ...)
    + Parse an XML document.  + Return values from this function depend on the SAX handler used.
    + Arguments: +

    + +

    + Common keyword arguments: +

    + + +

    +

    Function CXML:PARSE-DTD-FILE (pathname)
    +
    Function CXML:PARSE-DTD-STREAM (stream)
    + Parse     declarations + from a stand-alone file and return an object representing the DTD, + suitable as an argument to validate. +

    + + +

    +

    Function CXML:MAKE-EXTID (publicid systemid)
    + Create an object representing the External ID composed + of the specified Public ID, a rod or nil, and System ID + (an URI object). +

    + +

    +

    Function DOM:MAKE-DOM-BUILDER ()
    + Create a SAX handler which builds a DOM document.  Example: +

    + 
    (cxml:parse-file "test.xml" (dom:make-dom-builder))
    + + +

    Serialization

    +

    +

    Function CXML:UNPARSE-DOCUMENT (document stream &rest keys)
    +
    Function CXML:UNPARSE-DOCUMENT-TO-OCTETS (document &rest keys) => vector
    + Serialize a DOM document object. +

    + +

    Keyword arguments:

    + +

    + The following canonical values are allowed: +

    +     +

    + With an indentation level, pretty-print the XML by + inserting additional whitespace.  Note that indentation + changes the document model and should only be used if whitespace + does not matter to the application. +

    +

    + unparse-document-to-octets returns an (unsigned-byte + 8) array, whereas unparse-document writes + characters.  unparse-document is useful together + with with-output-to-string.  However, note that the + resulting document in both cases is UTF-8 encoded, so the + characters written by unparse-document are really UTF-8 + bytes encoded as characters. +

    + +

    +

    Function CXML:MAKE-CHARACTER-STREAM-SINK (stream &rest keys) => sink
    +
    Function CXML:MAKE-OCTET-VECTOR-SINK (&rest keys) => sink
    + Return a handle suitable for event-based XML serialization. +

    +

    + These function provide the low-level mechanism used by the DOM + serialization functions. To serialize a document without building + its DOM tree first, create a sink handle and call SAX functions on that + handle. sax:end-document returns the serialized form of + the document described by the SAX events. +

    + +

    +

    Macro CXML:WITH-XML-OUTPUT (sink &body body) => vector
    +
    Macro CXML:WITH-ELEMENT (qname &body body) => result
    +
    Function CXML:ATTRIBUTE (name value) => value
    +
    Function CXML:TEXT (data) => data
    +
    Function CXML:CDATA (data) => data
    + Convenience syntax for event-based serialization. +

    +

    + Example: +

    + 
    (with-xml-output (make-octet-stream-sink stream :indentation 2 :canonical nil)
+  (with-element "foo"
+    (attribute "xyz" "abc")
+    (with-element "bar"
+      (attribute "blub" "bla"))
+    (text "Hi there.")))
    +

    + Prints this to stream, which must be an + (unsigned-byte 8) stream: +

    + 
    <foo xyz="abc">
+  <bar blub="bla"></bar>
+  Hi there.
+</foo>
    +

    + (Note that these functions accept both strings and rods, so we + could write "foo" instead of #"foo" above.) +

    + +

    +

    Macro XHTML-GENERATOR:WITH-XHTML (sink &rest forms)
    +
    Macro XHTML-GENERATOR:WRITE-DOCTYPE (sink)
    + Macro with-xhtml is a modified version of + Franz' htmlgen works as a SAX driver for XHTML. + It aims to be a plug-in replacement for the html macro. +

    +

    + xhtmlgen is included as contrib/xhtmlgen.lisp in + the cxml distribution. Example: +

    + 
    (let ((sink (cxml:make-character-stream-sink *standard-output*)))
+  (sax:start-document sink)
+  (xhtml-generator:write-doctype sink)
+  (xhtml-generator:with-html sink
+    (:html
+     (:head
+      (:title "Titel"))
+     (:body
+      ((:p "style" "font-weight: bold")
+       "Inhalt")
+      (:ul
+       (:li "Eins")
+       (:li "Zwei")
+       (:li "Drei")))))
+  (sax:end-document sink))
    + + +

    Miscellaneous Utility Functions

    +

    +

    Function CXML:MAKE-VALIDATOR (dtd root)
    + Create a SAX handler which validates against a DTD instance.  + The document's root element must be named root.  + Used with dom:map-document, this validates a document + object as if by re-reading it with a validating parser, except + that declarations recorded in the document instance are completely + ignored.
    + Example: +

    + 
    (let ((d (parse-file "~/test.xml" (dom:make-dom-builder)))
+      (x (parse-dtd-file "~/test.dtd")))
+  (dom:map-document (cxml:make-validator x #"foo") d))
    + +

    +

    Function DOM:MAP-DOCUMENT (handler document &key include-xmlns-attributes include-default-values)
    + Traverse a DOM document and call SAX functions as if an XML + representation of the document were processed by a SAX parser. +

    + +

    +

    Class CXML:SAX-PROXY ()
    +
    Accessor CXML:PROXY-CHAINED-HANDLER
    + sax-proxy is a SAX handler which passes all events it + receives on to a user-defined second handler, which defaults + to nil. Use sax-proxy to modify the events a + SAX handler receives by defining your own subclass + of sax-proxy. Setting the chained handler to the target + handler, and define methods on your handler class for the events + to be modified. All other events will pass through to the chained + handler unmodified. +

    + +     +

    XMLS Compatibility

    +

    + Like other XML parsers written in Lisp, CXML can work with + documents represented as list structures. The specific model + implemented by cxml is compatible with the xmls parser. Xmls + list structures are a simpler and faster alternative to full DOM + document trees. They also serve as an example showing how to + implement user-defined document models as an independent layer + over the the base parser (c.f. xml/xmls-compat.lisp in + the cxml distribution). However, note that the list structures do + not include all information available in DOM documents and are + sometimes more difficult to work wth since many DOM functions + cannot be implemented on them. +

    +

    +

    Function CXML-XMLS:MAKE-XMLS-BUILDER (&key include-default-values)
    + Create a SAX handler which builds XMLS list structures.  + If include-default-values is true, default values for + attributes declared in a DTD are included as attributes in the + xmls output. include-default-values is true by default + and can be set to nil to suppress inclusion of default + values. +

    +

    + Example: +

    + 
    (cxml:parse-file "test.xml" (cxml-xmls:make-xmls-builder))
    +

    +

    Function CXML-XMLS:MAP-NODE (handler node &key include-xmlns-attributes)
    + Traverse an XMLS document/node and call SAX functions as if an XML + representation of the document were processed by a SAX parser. +

    +

    + Use this function to serialize XMLS data. For example, we could + define a replacement for xmls:write-xml like this: +

    + 
    (defun write-xml (stream node &key indent)
+  (let ((sink (cxml:make-character-stream-sink
+               stream :canonical nil :indentation indent)))
+    (cxml-xmls:map-node sink node)))
    +

    +

    Function CXML-XMLS:MAKE-NODE (&key name ns attrs + children) => xmls node
    + Build a list node of the form + (name ((name value)*) child*). +

    +

    + The node list's car can also be a cons of local name + and namespace prefix ns. + fixme: It is unclear to me how namespaces are meant to + work in xmls, since xmls documentation differs from how xmls + actually works in current releases. Usually applications need to + know both the namespace prefix and the namespace URI. We + currently follow the xmls implementation and use the + namespace prefix instead of following its documentation which + shows the URI. We do not follow xmls in munging xmlns attribute + values. Attributes themselves have namespaces and it is not clear + to me how that works in xmls. +

    +

    +

    Accessor CXML-XMLS:NODE-NAME (node)
    +
    Accessor CXML-XMLS:NODE-NS (node)
    +
    Accessor CXML-XMLS:NODE-ATTRS (node)
    +
    Accessor CXML-XMLS:NODE-CHILDREN (node)
    + Accessors for xmls node data. +

    +

    +

    + + +

    Dealing with Rods

    +

    + As explained above, the XML parser handles character encoding and + uses 16bit strings internally. Instead of using characters and strings + it uses runes and rods. This is seen as a + feature, but can be inconvenient. +

    + +

    + Note that the recoder approach does not work with the DOM + builder, since DOM is specified to use UTF-16. +

    +

    +

    Function CXML:MAKE-RECODER (chained-handler &optional recoder-fn)
    + Return a SAX handler which passes all events on to + chained-handler after converting all strings and rods + using recoder-fn, a function of one argument which + defaults to runes:rod-string. +

    +

    + Example. In a Lisp which ordinarily would use octet vector rods: +

    + 
    CL-USER(14): (cxml:parse-string "<test/>" (cxml-xmls:make-xmls-builder))
+(#(116 101 115 116) NIL)
    +

    + Use a SAX recoder to get strings instead:: +

    + 
    CL-USER(17): (parse-string "<test/>" (cxml:make-recoder (cxml-xmls:make-xmls-builder)))
+("test" NIL)
    + +     +

    Caching of DTD Objects

    +

    + To avoid spending time parsing the same DTD over and over again, + CXML can cache DTD objects. The parser consults + cxml:*dtd-cache* whenever it is looking for an external + subset in a document which does not have an internal subset and + uses the cached DTD instance if one is present in the cache for + the System ID in question. +

    +

    + Note that DTDs do not expire from the cache automatically. + (Future versions of CXML might introduce automatic checks for + outdated DTDs.) +

    +

    +

    Variable CXML:*DTD-CACHE*
    + The DTD cache object consulted by the parser when it needs a DTD. +

    +

    +

    Function CXML:MAKE-DTD-CACHE ()
    + Return a new, empty DTD cache object. +

    +

    +

    Variable CXML:*CACHE-ALL-DTDS*
    + If true, instructs the parser to enter all DTDs that could have + been cached into *dtd-cache* if they were not cached + already. Defaults to nil. +

    +

    +

    Reader CXML:GETDTD (uri dtd-cache)
    + Return a cached instance of the DTD at uri, if present in + the cache, or nil. +

    +

    +

    Writer CXML:GETDTD (uri dtd-cache)
    + Enter a new value for uri into dtd-cache. +

    +

    +

    Function CXML:REMDTD (uri dtd-cache)
    + Ensure that no DTD is recorded for uri in the cache and + return true if such a DTD was present. +

    +

    +

    Function CXML:CLEAR-DTD-CACHE (dtd-cache)
    + Remove all entries from dtd-cache. +

    +

    + fixme: thread-safety +

    + +     +

    XML Catalogs

    +

    + External entities (for example, DTDs) are referred to using their + Public and System IDs. Usually the System ID, a URI, is used to + locate the entity. CXML itself handles only file://-URIs, but + many System IDs in practical use are http://-URIs. There are two + different mechanims applications can use to allow CXML to locate + entities using arbitrary Public ID or System ID: +

    +     +

    + This section describes XML Catalogs, the second solution. CXML + implements Oasis + XML Catalogs. +

    +

    +

    Variable CXML:*CATALOG*
    + The XML Catalog object consulted by the parser before trying to + open an entity. Initially nil. +

    +

    +

    Variable CXML:*PREFER*
    + The default "prefer" mode from the Catalog specification, one + of :public or :system. Defaults + to :public. +

    +

    +

    Function CXML:MAKE-CATALOG (&optional uris)
    + Return a catalog object for the catalog files specified. +

    +

    +

    Function CXML:RESOLVE-URI (uri catalog)
    + Look up uri in catalog and return the + resulting URI, or nil if no match was found. +

    +

    +

    Function CXML:RESOLVE-EXTID (publicid systemid catalog)
    + Look up the External ID (publicid, systemid) + in catalog and return the resulting URI, or nil + if no match was found. +

    +

    + Example: +

    + 
    * (setf cxml:*catalog* nil)
+* (cxml:parse-file "test.xhtml" nil)
+=> Error: URI scheme :HTTP not supported
+
+* (setf cxml:*catalog* (cxml:make-catalog))
+* (cxml:parse-file "test.xhtml" nil)
+;; no error!
+NIL
    +

    + Note that parsed catalog files are cached in the catalog object. + Catalog files cached do not expire automatically. To ensure that + all catalog files are parsed again, create a new catalog object. +

    + + +

    SAX Interface

    +

    + A SAX handler is an arbitrary objects that implements some of the + generic functions in the SAX package.  Note that no default + handler class is necessary, because all generic functions have default + methods which do nothing.  SAX functions are: +

    Function SAX:START-DOCUMENT (handler)
    +
    Function SAX:END-DOCUMENT (handler)
    +
    +
    Function SAX:START-ELEMENT (handler namespace-uri local-name qname attributes)
    +
    Function SAX:END-ELEMENT (handler namespace-uri local-name qname)
    +
    Function SAX:START-PREFIX-MAPPING (handler prefix uri)
    +
    Function SAX:END-PREFIX-MAPPING (handler prefix)
    +
    Function SAX:PROCESSING-INSTRUCTION (handler target data)
    +
    Function SAX:COMMENT (handler data)
    +
    Function SAX:START-CDATA (handler)
    +
    Function SAX:END-CDATA (handler)
    +
    Function SAX:CHARACTERS (handler data)
    +
    +
    Function SAX:START-DTD (handler name public-id system-id)
    +
    Function SAX:END-DTD (handler)
    +
    Function SAX:UNPARSED-ENTITY-DECLARATION (handler name public-id system-id notation-name)
    +
    Function SAX:EXTERNAL-ENTITY-DECLARATION (handler kind name public-id system-id)
    +
    Function SAX:INTERNAL-ENTITY-DECLARATION (handler kind name value)
    +
    Function SAX:NOTATION-DECLARATION (handler name public-id system-id)
    +
    Function SAX:ELEMENT-DECLARATION (handler name model)
    +
    Function SAX:ATTRIBUTE-DECLARATION (handler ename aname type default)
    +
    +
    Accessor SAX:ATTRIBUTE-PREFIX (attribute)
    +
    Accessor SAX:ATTRIBUTE-NAMESPACE-URI (attribute)
    +
    Accessor SAX:ATTRIBUTE-LOCAL-NAME (attribute)
    +
    Accessor SAX:ATTRIBUTE-VALUE (attribute)
    +
    Accessor SAX:ATTRIBUTE-QNAME (attribute)
    +
    Accessor SAX:ATTRIBUTE-SPECIFIED-P (attribute)
    +

    +

    + The entity declaration methods are similar to Java SAX + definitions, but parameter entities are distinguished from + general entities not by a % prefix to the name, but by + the kind argument, either :parameter or + :general. +

    +

    + The arguments to sax:element-declaration and + sax:attribute-declaration differ significantly from their + Java counterparts. +

    +

    + fixme: For more information on these functions refer to the docstrings. +

    + + +     +

    DOM Notes

    +

    + CXML implements the DOM Level 1 Core interfaces.  Explaining + DOM is better left to the specification, + so please refer to the official W3C documents for DOM. +

    +

    + However, there is no "standard" DOM mapping for Lisp.  DOM + is specified + in CORBA IDL, but it refrains from using object-oriented IDL + features, allowing for a much more natural Lisp implemenation than + the the ordinary IDL/Lisp mapping would. +

    +

    + Differences between CXML's DOM and the direct IDL/Lisp mapping: +

    + +

    Example:

    + 
    XML(97): (dom:node-type
+          (dom:document-element
+           (cxml:parse-file "~/test.xml" (dom:make-dom-builder))))
+:ELEMENT
    + + diff --git a/runes/runes.lisp b/runes/runes.lisp index 620bb79..94b8f81 100644 --- a/runes/runes.lisp +++ b/runes/runes.lisp @@ -147,12 +147,17 @@ (defun char-rune (char) (code-rune (char-code char))) -(defun rune-char (rune &optional (default #\?)) - (if (>= rune char-code-limit) - default - (or (code-char rune) default))) +(defparameter *invalid-rune* nil ;;#\? + "Rune to use as a replacement in RUNE-CHAR and ROD-STRING for runes not + representable as characters. If NIL, an error is signalled instead.") -(defun rod-string (rod &optional (default-char #\?)) +(defun rune-char (rune &optional (default *invalid-rune*)) + (or (if (>= rune char-code-limit) + default + (or (code-char rune) default)) + (error "rune cannot be represented as a character: ~A" rune))) + +(defun rod-string (rod &optional (default-char *invalid-rune*)) (map 'string (lambda (x) (rune-char x default-char)) rod)) (defun string-rod (string) diff --git a/test/domtest.lisp b/test/domtest.lisp index 478048a..4692358 100644 --- a/test/domtest.lisp +++ b/test/domtest.lisp @@ -126,28 +126,29 @@ (map-child-elements 'list #'identity element)) (defun parse-java-literal (str) - (unless (stringp str) - (setf str (runes:rod-string str))) + (when (stringp str) + (setf str (runes:string-rod str))) (cond ((zerop (length str)) nil) - ((equal str "true") + ((runes:rod= str #"true") t) - ((equal str "false") + ((runes:rod= str #"false") nil) - ((digit-char-p (char str 0)) - (parse-integer str)) - ((char= (char str 0) #\") - (runes:rod - (with-output-to-string (out) - (with-input-from-string (in str) - (read-char in) - (for ((c = (read-char in)) - :until (char= c #\")) - (if (char= c #\\) - (ecase (read-char in) - ;; ... - (#\n (write-char #\newline out))) - (write-char c out))))))) + ((digit-char-p (runes:rune-char (elt str 0))) + (parse-integer (runes:rod-string str))) + ((runes:rune= (elt str 0) #.(runes:char-rune #\")) + (let ((v (make-array 1 :fill-pointer 0 :adjustable t))) + (for* ((i = 1 :then (1+ i)) + (c = (elt str i)) + :until (runes:rune= c #.(runes:char-rune #\"))) + (if (runes:rune= c #.(runes:char-rune #\\)) + (ecase (progn + (incf i) + (elt str i)) + ;; ... + (#/n (vector-push-extend #/newline v (length v)))) + (vector-push-extend c v (length v)))) + (coerce v 'runes::simple-rod))) (t (%intern str)))) @@ -613,7 +614,8 @@ document)) (defparameter *bad-tests* - '("hc_nodereplacechildnewchildexists.xml" + '("hc_elementnormalize2.xml" + "hc_nodereplacechildnewchildexists.xml" "characterdatadeletedatanomodificationallowederr.xml")) (defun run-all-tests (*directory* &optional verbose) @@ -635,7 +637,7 @@ (incf n))) (do-child-elements (member suite) (let ((href (runes:rod-string (dom:get-attribute member "href")))) - (unless (or (equal (dom:tag-name member) "metadata") + (unless (or (runes:rod= (dom:tag-name member) #"metadata") (member href *bad-tests* :test 'equal)) (format t "~&~D/~D ~A~%" i n href) (let ((lisp (slurp-test (merge-pathnames href test-directory))))