From 067bae5ff8f715ce895e0cecf8c5b4b6b2f5e218 Mon Sep 17 00:00:00 2001 From: Daniel Veillard Date: Sun, 5 Jan 2003 01:27:54 +0000 Subject: [PATCH] seriously changed the way data are pushed to the underlying parser, go by * xmlreader.c: seriously changed the way data are pushed to the underlying parser, go by block of 512 bytes instead of tryng to detect tag boundaries at that level. Changed the way empty element are detected and tagged. * python/tests/reader.py python/tests/reader2.py python/tests/reader3.py: small changes mostly due to context reporting being different and DTD node being reported. Some errors previously undetected are now caught and fixed. * doc/xmlreader.html: flagged last section as TODO Daniel --- ChangeLog | 12 +++++++ doc/xmlreader.html | 2 ++ python/tests/reader.py | 30 ++++++++-------- python/tests/reader2.py | 22 +++++++----- python/tests/reader3.py | 12 ++++++- xmlreader.c | 80 +++++++++++++---------------------------- 6 files changed, 78 insertions(+), 80 deletions(-) diff --git a/ChangeLog b/ChangeLog index 67cc881f..1524135a 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,15 @@ +Sun Jan 5 02:23:20 CET 2003 Daniel Veillard + + * xmlreader.c: seriously changed the way data are pushed to + the underlying parser, go by block of 512 bytes instead of + tryng to detect tag boundaries at that level. Changed the + way empty element are detected and tagged. + * python/tests/reader.py python/tests/reader2.py + python/tests/reader3.py: small changes mostly due to context + reporting being different and DTD node being reported. Some + errors previously undetected are now caught and fixed. + * doc/xmlreader.html: flagged last section as TODO + Sat Jan 4 20:40:28 CET 2003 Daniel Veillard * python/libxml.py: integrated the Python 2.2 optimizations diff --git a/doc/xmlreader.html b/doc/xmlreader.html index e818a77c..b44a3ea8 100644 --- a/doc/xmlreader.html +++ b/doc/xmlreader.html @@ -390,6 +390,8 @@ the validation feature is just:

Entities substitution

+

@@TODO@@

+

Daniel Veillard

diff --git a/python/tests/reader.py b/python/tests/reader.py index 5fd61603..e9671718 100755 --- a/python/tests/reader.py +++ b/python/tests/reader.py @@ -14,56 +14,56 @@ input = libxml2.inputBuffer(f) reader = input.newTextReader("test1") ret = reader.Read() if ret != 1: - print "Error reading to first element" + print "test1: Error reading to first element" sys.exit(1) if reader.Name() != "a" or reader.IsEmptyElement() != 0 or \ reader.NodeType() != 1 or reader.HasAttributes() != 0: - print "Error reading the first element" + print "test1: Error reading the first element" sys.exit(1) ret = reader.Read() if ret != 1: - print "Error reading to second element" + print "test1: Error reading to second element" sys.exit(1) if reader.Name() != "b" or reader.IsEmptyElement() != 1 or \ reader.NodeType() != 1 or reader.HasAttributes() != 1: - print "Error reading the second element" + print "test1: Error reading the second element" sys.exit(1) ret = reader.Read() if ret != 1: - print "Error reading to third element" + print "test1: Error reading to third element" sys.exit(1) if reader.Name() != "c" or reader.IsEmptyElement() != 0 or \ reader.NodeType() != 1 or reader.HasAttributes() != 0: - print "Error reading the third element" + print "test1: Error reading the third element" sys.exit(1) ret = reader.Read() if ret != 1: - print "Error reading to text node" + print "test1: Error reading to text node" sys.exit(1) if reader.Name() != "#text" or reader.IsEmptyElement() != 0 or \ reader.NodeType() != 3 or reader.HasAttributes() != 0 or \ reader.Value() != "content of c": - print "Error reading the text node" + print "test1: Error reading the text node" sys.exit(1) ret = reader.Read() if ret != 1: - print "Error reading to end of third element" + print "test1: Error reading to end of third element" sys.exit(1) if reader.Name() != "c" or reader.IsEmptyElement() != 0 or \ reader.NodeType() != 15 or reader.HasAttributes() != 0: - print "Error reading the end of third element" + print "test1: Error reading the end of third element" sys.exit(1) ret = reader.Read() if ret != 1: - print "Error reading to end of first element" + print "test1: Error reading to end of first element" sys.exit(1) if reader.Name() != "a" or reader.IsEmptyElement() != 0 or \ reader.NodeType() != 15 or reader.HasAttributes() != 0: - print "Error reading the end of first element" + print "test1: Error reading the end of first element" sys.exit(1) ret = reader.Read() if ret != 0: - print "Error reading to end of document" + print "test1: Error reading to end of document" sys.exit(1) # @@ -239,7 +239,7 @@ if reader.MoveToNextAttribute() != 0: # # a couple of tests for namespace nodes # -f = StringIO.StringIO("""""") +f = StringIO.StringIO("""""") input = libxml2.inputBuffer(f) reader = input.newTextReader("test6") ret = reader.Read() @@ -256,7 +256,7 @@ if reader.NamespaceUri() != "http://www.w3.org/2000/xmlns/" or \ print "test6: failed to read the namespace node" sys.exit(1) -f = StringIO.StringIO("""""") +f = StringIO.StringIO("""""") input = libxml2.inputBuffer(f) reader = input.newTextReader("test7") ret = reader.Read() diff --git a/python/tests/reader2.py b/python/tests/reader2.py index 6333aee4..7519a901 100755 --- a/python/tests/reader2.py +++ b/python/tests/reader2.py @@ -14,13 +14,13 @@ libxml2.debugMemory(1) err="" expect="""../../test/valid/rss.xml:172: validity error: Element rss does not carry attribute version - ^ + ^ ../../test/valid/xlink.xml:450: validity error: ID dt-arc already defined -

+

An arc is contained within an ^ -../../test/valid/xlink.xml:529: validity error: attribute def line 199 references an unknown ID "dt-xlg" - - ^ +../../test/valid/xlink.xml:530: validity error: attribute def line 199 references an unknown ID "dt-xlg" + +^ """ def callback(ctx, str): global err @@ -61,7 +61,8 @@ s = """ bbb """ -expect="""1,test +expect="""10,test +1,test 3,#text 1,x 1,c @@ -110,7 +111,8 @@ s = """ """ tst_ent = """hello""" -expect="""1 test +expect="""10 test +1 test 3 #text 1 x 3 #text @@ -161,7 +163,8 @@ s = """""" -expect="""1 test 0 +expect="""10 test 0 +1 test 0 3 #text 1 1 x 1 1 y 2 @@ -213,7 +216,8 @@ s = """""" -expect="""1 test 0 +expect="""10 test 0 +1 test 0 3 #text 1 5 x 1 3 #text 1 diff --git a/python/tests/reader3.py b/python/tests/reader3.py index 1affbe98..2a4fbe07 100755 --- a/python/tests/reader3.py +++ b/python/tests/reader3.py @@ -1,6 +1,6 @@ #!/usr/bin/python -u # -# this tests the validation with the XmlTextReader interface +# this tests the entities substitutions with the XmlTextReader interface # import sys import StringIO @@ -22,6 +22,11 @@ f = StringIO.StringIO(docstr) input = libxml2.inputBuffer(f) reader = input.newTextReader("test_noent") ret = reader.Read() +if ret != 1: + print "Error reading to root" + sys.exit(1) +if reader.Name() == "doc" or reader.NodeType() == 10: + ret = reader.Read() if ret != 1: print "Error reading to root" sys.exit(1) @@ -55,6 +60,11 @@ input = libxml2.inputBuffer(f) reader = input.newTextReader("test_noent") reader.SetParserProp(libxml2.PARSER_SUBST_ENTITIES, 1) ret = reader.Read() +if ret != 1: + print "Error reading to root" + sys.exit(1) +if reader.Name() == "doc" or reader.NodeType() == 10: + ret = reader.Read() if ret != 1: print "Error reading to root" sys.exit(1) diff --git a/xmlreader.c b/xmlreader.c index 0577334b..316ff15a 100644 --- a/xmlreader.c +++ b/xmlreader.c @@ -15,6 +15,8 @@ * - provide an API to expand part of the tree * - provide an API to preserve part of the tree * - Streaming XInclude support + * - validation against a provided DTD + * - XML Schemas validation * - setting(s) for NoBlanks * - performances and tuning ... */ @@ -99,7 +101,6 @@ struct _xmlTextReader { xmlNodePtr curnode;/* current attribute node */ int depth; /* depth of the current node */ xmlNodePtr faketext;/* fake xmlNs chld */ - int wasempty;/* was the last node empty */ /* entity stack when traversing entities content */ xmlNodePtr ent; /* Current Entity Ref Node */ @@ -108,6 +109,8 @@ struct _xmlTextReader { xmlNodePtr *entTab; /* array of entities */ }; +static const char *xmlTextReaderIsEmpty = "This element is empty"; + #ifdef DEBUG_READER static void xmlTextReaderDebug(xmlTextReaderPtr reader) { @@ -222,13 +225,10 @@ xmlTextReaderStartElement(void *ctx, const xmlChar *fullname, */ origctxt = reader->ctxt; reader->startElement(ctx, fullname, atts); -#if 0 - 123 - if (origctxt->validate) { - ctxt->valid &= xmlValidatePushElement(&origctxt->vctxt, - ctxt->myDoc, ctxt->node, fullname); - } -#endif + if ((ctxt->node != NULL) && (ctxt->input != NULL) && + (ctxt->input->cur != NULL) && (ctxt->input->cur[0] == '/') && + (ctxt->input->cur[1] == '>')) + ctxt->node->_private = (void *) xmlTextReaderIsEmpty; } if (reader != NULL) reader->state = XML_TEXTREADER_ELEMENT; @@ -258,12 +258,6 @@ xmlTextReaderEndElement(void *ctx, const xmlChar *fullname) { reader->endElement(ctx, fullname); } - if (reader != NULL) { - if (reader->state == XML_TEXTREADER_ELEMENT) - reader->wasempty = 1; - else - reader->wasempty = 0; - } } /** @@ -290,13 +284,6 @@ xmlTextReaderCharacters(void *ctx, const xmlChar *ch, int len) * when processing an entity, the context may have been changed */ origctxt = reader->ctxt; - -#if 0 - 123 - if (origctxt->validate) { - ctxt->valid &= xmlValidatePushCData(&origctxt->vctxt, ch, len); - } -#endif } } @@ -319,10 +306,6 @@ xmlTextReaderCDataBlock(void *ctx, const xmlChar *ch, int len) #endif if ((reader != NULL) && (reader->cdataBlock != NULL)) { reader->cdataBlock(ctx, ch, len); - - if (ctxt->validate) { - ctxt->valid &= xmlValidatePushCData(&ctxt->vctxt, ch, len); - } } } @@ -365,8 +348,12 @@ xmlTextReaderPushData(xmlTextReaderPtr reader) { } else break; } - if (inbuf->content[cur] == '>') { - cur = cur + 1; + /* + * parse by block of 512 bytes + */ + if ((cur >= reader->cur + 512) || (cur >= inbuf->use)) { + if (cur < inbuf->use) + cur = cur + 1; val = xmlParseChunk(reader->ctxt, (const char *) &inbuf->content[reader->cur], cur - reader->cur, 0); @@ -412,7 +399,9 @@ xmlTextReaderPushData(xmlTextReaderPtr reader) { if (reader->mode == XML_TEXTREADER_MODE_EOF) { if (reader->mode != XML_TEXTREADER_DONE) { val = xmlParseChunk(reader->ctxt, - (const char *) &inbuf->content[reader->cur], 0, 1); + (const char *) &inbuf->content[reader->cur], + cur - reader->cur, 1); + reader->cur = cur; reader->mode = XML_TEXTREADER_DONE; } } @@ -564,7 +553,7 @@ xmlTextReaderValidateEntity(xmlTextReaderPtr reader) { */ int xmlTextReaderRead(xmlTextReaderPtr reader) { - int val, olddepth = 0, wasempty = 0; + int val, olddepth = 0; xmlTextReaderState oldstate = 0; xmlNodePtr oldnode = NULL; @@ -588,14 +577,11 @@ xmlTextReaderRead(xmlTextReaderPtr reader) { if (val < 0) return(-1); } while ((reader->ctxt->node == NULL) && - (reader->mode != XML_TEXTREADER_MODE_EOF)); + ((reader->mode != XML_TEXTREADER_MODE_EOF) && + (reader->mode != XML_TEXTREADER_DONE))); if (reader->ctxt->node == NULL) { if (reader->ctxt->myDoc != NULL) { reader->node = reader->ctxt->myDoc->children; - if ((reader->ctxt->input != NULL) && - (reader->ctxt->input->cur != NULL) && - (reader->ctxt->input->cur[-2] != '/')) - reader->wasempty = -1; } if (reader->node == NULL) return(-1); @@ -610,16 +596,6 @@ xmlTextReaderRead(xmlTextReaderPtr reader) { oldstate = reader->state; olddepth = reader->ctxt->nodeNr; oldnode = reader->node; - /* - * the

vs.

distinction at the API level royally sucks, - * Microsoft priviledge ... - */ - if (reader->wasempty == -1) - wasempty = 0; - else - wasempty = (((reader->wasempty == 1) && (reader->ctxt->node != NULL) && - (reader->ctxt->node->last == reader->node)) || - (reader->node != reader->ctxt->node)); get_next_node: /* @@ -653,7 +629,8 @@ get_next_node: if (reader->node->next != NULL) { if ((oldstate == XML_TEXTREADER_ELEMENT) && (reader->node->type == XML_ELEMENT_NODE) && - (wasempty == 0)) { + (reader->node->children == NULL) && + (reader->node->_private != (void *)xmlTextReaderIsEmpty)) { reader->state = XML_TEXTREADER_END; goto node_found; } @@ -675,7 +652,8 @@ get_next_node: } if ((oldstate == XML_TEXTREADER_ELEMENT) && (reader->node->type == XML_ELEMENT_NODE) && - (wasempty == 0)) { + (reader->node->children == NULL) && + (reader->node->_private != (void *)xmlTextReaderIsEmpty)) { reader->state = XML_TEXTREADER_END; goto node_found; } @@ -1733,15 +1711,7 @@ xmlTextReaderIsEmptyElement(xmlTextReaderPtr reader) { return(0); if (reader->state == XML_TEXTREADER_END) return(0); - if (reader->wasempty == -1) - return(0); - if (reader->node != reader->ctxt->node) - return(1); - if ((reader->ctxt->node != NULL) && - (reader->node == reader->ctxt->node->last) && - (reader->wasempty == 1)) - return(1); - return(0); + return(reader->node->_private == (void *)xmlTextReaderIsEmpty); } /**