Hello
libxml-ruby's SAX parser interface is only of limited use currently. The
reason is that the document to be parsed must be passed as a whole. This
is somewhat contrary to the actual reason for the use of a SAX parser.
The attached patch adds a new constructor to use the parser in the
so-called "push mode" where it won't complain about the document to be
unfinished when parsing subsequent parts of it.
My goal was the parsing of a network XML stream (XMPP). Here, the
document is being provided continually over time and I need the SAX
events long before the document ends. :-)
Unfortunately, the libxml parser seems to buffer a lot and I don't
receive all events of the current string immediately. This behaviour
renders it unsuitable for XMPP and I will stick to the apparently
antique expat binding unless someone comes up with a better idea.
Stephan
>From 7b70b3f4bd2c212c7750ca22f175b1510451825b Mon Sep 17 00:00:00 2001
From: Stephan Maka <[EMAIL PROTECTED]>
Date: Sat, 27 Sep 2008 00:32:07 +0200
Subject: [PATCH] ruby_xml_sax_parser_new_push_parser
---
ext/libxml/ruby_xml_sax_parser.c | 50 +++++++++++++++++++++++++++++++++++--
ext/libxml/ruby_xml_sax_parser.h | 1 +
2 files changed, 48 insertions(+), 3 deletions(-)
diff --git a/ext/libxml/ruby_xml_sax_parser.c b/ext/libxml/ruby_xml_sax_parser.c
index 26921c6..2515dbf 100644
--- a/ext/libxml/ruby_xml_sax_parser.c
+++ b/ext/libxml/ruby_xml_sax_parser.c
@@ -33,6 +33,12 @@ ruby_xml_sax_parser_free(ruby_xml_sax_parser *nodesp) {
/* Apparently this isn't needed: time will tell */
/* if (nodesp->xsh != NULL) */
/* xmlFreeSax_Parser(nodesp->sax_parser); */
+
+ if (nodesp->push_parser && nodesp->xpc)
+ {
+ xmlParseChunk(nodesp->xpc, NULL, 0, 1);
+ xmlFreeParserCtxt(nodesp->xpc);
+ }
}
void
@@ -61,6 +67,7 @@ ruby_xml_sax_parser_new(VALUE class) {
ruby_xml_sax_parser *nodesp;
nodesp = ALLOC(ruby_xml_sax_parser);
+ nodesp->push_parser = 0;
nodesp->xsh = &rubySAXHandlerStruct;
nodesp->callbackHandler = Qnil;
@@ -72,6 +79,28 @@ ruby_xml_sax_parser_new(VALUE class) {
ruby_xml_sax_parser_free, nodesp));
}
+/*
+ * call-seq:
+ * XML::SaxParser.new -> sax_parser
+ *
+ * Create a new XML::SaxParser instance.
+ */
+VALUE
+ruby_xml_sax_parser_new_push_parser(VALUE class) {
+ ruby_xml_sax_parser *nodesp;
+
+ nodesp = ALLOC(ruby_xml_sax_parser);
+ nodesp->push_parser = 1;
+ nodesp->xsh = &rubySAXHandlerStruct;
+
+ nodesp->callbackHandler = Qnil;
+ nodesp->xpc = NULL;
+ nodesp->filename = Qnil;
+ nodesp->str = Qnil;
+
+ return(Data_Wrap_Struct(class, ruby_xml_sax_parser_mark,
+ ruby_xml_sax_parser_free, nodesp));
+}
/*
* call-seq:
@@ -154,9 +183,23 @@ ruby_xml_sax_parser_parse(VALUE self) {
status = xmlSAXUserParseFile(nodesp->xsh, nodesp,
StringValuePtr(nodesp->filename));
} else if (nodesp->str != Qnil) {
str = StringValuePtr(nodesp->str);
- status = //ruby_xml_document_new(cXMLDocument,
- xmlSAXUserParseMemory(nodesp->xsh, nodesp,
- str, strlen(str)); //);
+ if (nodesp->push_parser)
+ {
+ if (!nodesp->xpc)
+ {
+ printf("new push: %s\n", str);
+ status = (nodesp->xpc = xmlCreatePushParserCtxt(nodesp->xsh, nodesp,
str, strlen(str), "push.xml")) == NULL;
+ }
+ else
+ {
+ printf("push: %s\n", str);
+ status = xmlParseChunk(nodesp->xpc, str, strlen(str), 0) <= 0;
+ }
+ }
+ else
+ status = //ruby_xml_document_new(cXMLDocument,
+ xmlSAXUserParseMemory(nodesp->xsh, nodesp,
+ str, strlen(str)); //);
}
/* XXX This should return an exception for the various error codes
@@ -417,6 +460,7 @@ ruby_init_xml_sax_parser(void) {
/* SaxParser */
rb_define_singleton_method(cXMLSaxParser, "new", ruby_xml_sax_parser_new, 0);
+ rb_define_singleton_method(cXMLSaxParser, "new_push_parser",
ruby_xml_sax_parser_new_push_parser, 0);
rb_define_method(cXMLSaxParser, "filename",
ruby_xml_sax_parser_filename_get, 0);
diff --git a/ext/libxml/ruby_xml_sax_parser.h b/ext/libxml/ruby_xml_sax_parser.h
index 2d20ad0..8593b7a 100644
--- a/ext/libxml/ruby_xml_sax_parser.h
+++ b/ext/libxml/ruby_xml_sax_parser.h
@@ -41,6 +41,7 @@ typedef struct ruby_xml_sax_parser_callbacks {
*/
typedef struct ruby_xml_sax_parser {
+ int push_parser;
xmlParserCtxtPtr xpc;
xmlSAXHandlerPtr xsh;
//ruby_xml_sax_parser_callbacks *cbp;
--
1.5.6.5
_______________________________________________
libxml-devel mailing list
libxml-devel@rubyforge.org
http://rubyforge.org/mailman/listinfo/libxml-devel
