diff --git a/ChangeLog b/ChangeLog index d285e391..726f7f2d 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,14 @@ +Tue Oct 27 01:15:39 EST 1998 Daniel Veillard + + * parser.[ch] SAX.c tree.[ch]: large amount of changes to improve + entity support and provide an internal representation close to + DOM one (entity ref nodes, and attribute value as tree). I tried + to preserve the interface but this will surely break some apps + (I have to change rpm2html/rpmfind for example). I had to change + two interfaces, and the generated tree is somewhat different. + * doc/* : started documenting the XML library, the tree and + DOM/Corba. This is a first step. + Sat Oct 24 14:23:51 EDT 1998 Daniel Veillard * parser.c: Set up the fonctions comment block, boring but useful. diff --git a/SAX.c b/SAX.c index 56585ebd..9b7e504f 100644 --- a/SAX.c +++ b/SAX.c @@ -8,6 +8,7 @@ #include #include "tree.h" #include "parser.h" +#include "entities.h" #include "error.h" /* #define DEBUG_SAX */ @@ -85,8 +86,11 @@ xmlSAXLocator xmlDefaultSAXLocator = { * * Special entity resolver, better left to the parser, it has * more context than the application layer. + * The default behaviour is to NOT resolve the entities, in that case + * the ENTITY_REF nodes are built in the structure (and the parameter + * values). * - * return values: an int + * return values: the xmlParserInputPtr if inlined or NULL for DOM behaviour. */ xmlParserInputPtr resolveEntity(xmlParserCtxtPtr ctxt, const CHAR *publicId, const CHAR *systemId) @@ -95,6 +99,7 @@ resolveEntity(xmlParserCtxtPtr ctxt, const CHAR *publicId, const CHAR *systemId) #ifdef DEBUG_SAX fprintf(stderr, "SAX.resolveEntity(%s, %s)\n", publicId, systemId); #endif + return(NULL); } @@ -206,16 +211,9 @@ endDocument(xmlParserCtxtPtr ctxt) void startElement(xmlParserCtxtPtr ctxt, const CHAR *name) { - xmlNodePtr parent; - #ifdef DEBUG_SAX fprintf(stderr, "SAX.startElement(%s)\n", name); #endif - if (ctxt->nodeNr < 2) return; - parent = ctxt->nodeTab[ctxt->nodeNr - 2]; - if (parent != NULL) - xmlAddChild(parent, ctxt->node); - } /** @@ -254,7 +252,6 @@ attribute(xmlParserCtxtPtr ctxt, const CHAR *name, const CHAR *value) #ifdef DEBUG_SAX fprintf(stderr, "SAX.attribute(%s, %s)\n", name, value); #endif - xmlNewProp(ctxt->node, name, value); } /** diff --git a/doc/DOM.fig b/doc/DOM.fig new file mode 100644 index 00000000..7a48a329 --- /dev/null +++ b/doc/DOM.fig @@ -0,0 +1,64 @@ +#FIG 3.2 +Landscape +Center +Inches +Letter +100.00 +Single +-2 +1200 2 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 825 1125 2625 1125 2625 3375 825 3375 825 1125 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 4125 1125 5925 1125 5925 3375 4125 3375 4125 1125 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 2025 3075 2025 1650 1050 1650 1050 3075 2025 3075 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 1425 1875 1575 1875 1575 2025 1425 2025 1425 1875 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 1200 2175 1350 2175 1350 2325 1200 2325 1200 2175 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 1500 2175 1650 2175 1650 2325 1500 2325 1500 2175 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 1800 2175 1950 2175 1950 2325 1800 2325 1800 2175 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 1500 2475 1650 2475 1650 2625 1500 2625 1500 2475 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 1725 2700 1875 2700 1875 2850 1725 2850 1725 2700 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 1275 2700 1425 2700 1425 2850 1275 2850 1275 2700 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1500 2025 1350 2175 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1500 2025 1575 2175 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1500 2025 1875 2175 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1575 2325 1575 2475 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1650 2625 1725 2700 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1500 2625 1425 2700 +2 3 0 2 0 7 0 0 -1 6.000 0 0 -1 0 0 5 + 2550 1725 2175 1950 2175 2850 2550 3075 2550 1725 +2 3 0 2 0 7 0 0 -1 6.000 0 0 -1 0 0 5 + 4575 1725 4200 1950 4200 2850 4575 3075 4575 1725 +2 2 0 1 0 7 0 0 -1 4.000 0 0 -1 0 0 5 + 2700 2025 4050 2025 4050 2775 2700 2775 2700 2025 +2 1 0 2 0 7 0 0 -1 6.000 0 0 -1 0 0 2 + 5025 2025 4575 2175 +2 1 1 2 0 7 0 0 -1 6.000 0 0 -1 1 0 3 + 1 1 2.00 120.00 240.00 + 4575 2175 4200 2250 2025 2250 +2 1 1 2 0 7 0 0 -1 6.000 0 0 -1 0 0 3 + 2025 2475 4200 2475 4575 2550 +2 1 0 2 0 7 0 0 -1 6.000 0 0 -1 1 0 2 + 1 1 2.00 120.00 240.00 + 4575 2550 5025 2625 +4 0 0 0 0 0 18 0.0000 4 255 1155 1050 825 Program 1\001 +4 0 0 0 0 0 18 0.0000 4 255 1155 4425 900 Program 2\001 +4 0 0 0 0 0 18 0.0000 4 195 585 1350 1500 XML\001 +4 0 0 0 0 0 18 0.0000 4 195 975 3000 3075 CORBA\001 +4 0 0 0 0 0 18 0.0000 4 195 735 3000 3375 ORBit\001 +4 0 0 0 0 0 18 0.0000 4 195 1395 2175 1575 DOM server\001 +4 0 0 0 0 0 18 0.0000 4 195 1335 4200 1650 DOM client\001 diff --git a/doc/DOM.gif b/doc/DOM.gif new file mode 100644 index 00000000..a44882fe Binary files /dev/null and b/doc/DOM.gif differ diff --git a/doc/structure.fig b/doc/structure.fig new file mode 100644 index 00000000..34f6237c --- /dev/null +++ b/doc/structure.fig @@ -0,0 +1,303 @@ +#FIG 3.2 +Landscape +Center +Inches +Letter +100.00 +Single +-2 +1200 2 +6 1275 4425 5475 5100 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 2250 5100 2250 4425 1275 4425 1275 5100 2250 5100 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 3975 5100 3975 4425 3000 4425 3000 5100 3975 5100 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 5475 5100 5475 4425 4500 4425 4500 5100 5475 5100 +4 0 0 0 0 14 16 0.0000 4 135 600 4650 4725 TEXT\001 +4 0 0 0 0 14 16 0.0000 4 135 600 1425 4725 TEXT\001 +4 0 0 0 0 14 16 0.0000 4 135 900 3075 4725 ENTITY\001 +4 0 0 0 0 14 16 0.0000 4 135 450 3075 4950 REF\001 +-6 +6 825 4575 900 5100 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 900 4575 900 5100 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 900 5025 825 5100 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 900 4950 825 5025 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 900 4800 825 4875 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 900 4875 825 4950 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 900 4650 825 4725 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 900 4725 825 4800 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 900 4575 825 4650 +-6 +6 1125 2325 1200 2850 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1200 2325 1200 2850 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1200 2775 1125 2850 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1200 2700 1125 2775 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1200 2550 1125 2625 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1200 2625 1125 2700 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1200 2400 1125 2475 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1200 2475 1125 2550 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 1200 2325 1125 2400 +-6 +6 2550 4650 2625 5175 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2625 4650 2625 5175 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2625 5100 2550 5175 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2625 5025 2550 5100 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2625 4875 2550 4950 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2625 4950 2550 5025 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2625 4725 2550 4800 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2625 4800 2550 4875 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2625 4650 2550 4725 +-6 +6 6000 4200 6075 4725 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 6075 4200 6075 4725 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 6075 4650 6000 4725 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 6075 4575 6000 4650 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 6075 4425 6000 4500 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 6075 4500 6000 4575 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 6075 4275 6000 4350 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 6075 4350 6000 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 6075 4200 6000 4275 +-6 +6 2475 4425 2550 4950 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2475 4950 2475 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2475 4500 2550 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2475 4575 2550 4500 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2475 4725 2550 4650 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2475 4650 2550 4575 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2475 4875 2550 4800 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2475 4800 2550 4725 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 2475 4950 2550 4875 +-6 +6 5775 4425 5850 4950 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 5775 4950 5775 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 5775 4500 5850 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 5775 4575 5850 4500 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 5775 4725 5850 4650 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 5775 4650 5850 4575 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 5775 4875 5850 4800 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 5775 4800 5850 4725 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 5775 4950 5850 4875 +-6 +6 9000 2100 9075 2625 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 9000 2625 9000 2100 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 9000 2175 9075 2100 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 9000 2250 9075 2175 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 9000 2400 9075 2325 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 9000 2325 9075 2250 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 9000 2550 9075 2475 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 9000 2475 9075 2400 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 9000 2625 9075 2550 +-6 +6 11850 4050 11925 4575 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 11850 4575 11850 4050 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 11850 4125 11925 4050 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 11850 4200 11925 4125 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 11850 4350 11925 4275 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 11850 4275 11925 4200 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 11850 4500 11925 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 11850 4425 11925 4350 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 2 + 11850 4575 11925 4500 +-6 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 3150 375 4425 375 4425 1275 3150 1275 3150 375 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 2850 2775 2850 2100 1875 2100 1875 2775 2850 2775 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 5550 2775 5550 2100 4575 2100 4575 2775 5550 2775 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 8175 2775 8175 2100 7200 2100 7200 2775 8175 2775 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 7650 4725 7650 4050 6675 4050 6675 4725 7650 4725 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 9675 4725 9675 4050 8700 4050 8700 4725 9675 4725 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3750 1275 2400 2100 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 2850 2325 4575 2325 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 5550 2325 7200 2325 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 8175 2325 9000 2325 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 7200 2550 5550 2550 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 4575 2550 2850 2550 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 1875 2550 1200 2550 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 2250 2100 3525 1275 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 5100 2100 4050 1275 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 7725 2100 4125 1275 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 7725 2775 7125 4050 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 7650 4275 8700 4275 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 8700 4425 7650 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 9675 4275 10275 4275 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 6675 4500 6075 4500 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 1275 3375 2250 3375 2250 3825 1275 3825 1275 3375 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 3000 3375 3975 3375 3975 3825 3000 3825 3000 3375 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 2325 2775 1725 3375 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 2250 3600 3000 3600 +2 4 0 1 0 7 0 0 -1 0.000 0 0 7 0 0 5 + 11250 4725 11250 4050 10275 4050 10275 4725 11250 4725 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 11250 4275 11850 4275 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 10275 4425 9675 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 1725 3825 1725 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3450 3825 3450 4425 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3975 4650 4500 4650 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 5475 4650 5775 4650 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 4500 4875 3975 4875 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 2250 4650 2550 4650 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 1275 4875 900 4875 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 975 5625 2550 5625 2550 5850 975 5850 975 5625 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 4200 5625 5775 5625 5775 5850 4200 5850 4200 5625 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 6450 5250 8025 5250 8025 5475 6450 5475 6450 5250 +2 2 0 1 0 7 0 0 -1 0.000 0 0 -1 0 0 5 + 10125 5250 11700 5250 11700 5475 10125 5475 10125 5250 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 1725 5100 1725 5625 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 4875 5100 4875 5625 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 7050 4725 7050 5250 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 10650 4725 10650 5250 +2 1 0 1 0 7 0 0 -1 0.000 0 0 -1 1 0 2 + 1 1 1.00 60.00 120.00 + 3000 4875 2625 4875 +4 0 0 0 0 0 16 0.0000 4 150 420 3000 2250 next\001 +4 0 0 0 0 0 16 0.0000 4 180 450 3975 2775 prev\001 +4 0 0 0 0 0 16 0.0000 4 210 630 5100 2025 parent\001 +4 0 0 0 0 14 15 0.0000 4 135 945 7200 2475 ELEMENT\001 +4 0 0 0 0 14 15 0.0000 4 135 945 4575 2475 ELEMENT\001 +4 0 0 0 0 14 15 0.0000 4 135 945 1875 2475 ELEMENT\001 +4 0 0 0 0 14 16 0.0000 4 135 450 8775 4590 REF\001 +4 0 0 0 0 14 16 0.0000 4 135 900 8775 4350 ENTITY\001 +4 0 0 0 0 14 16 0.0000 4 135 600 10350 4425 TEXT\001 +4 0 0 0 0 14 16 0.0000 4 135 600 6750 4425 TEXT\001 +4 0 0 0 0 14 16 0.0000 4 150 1050 1275 2025 xmlNode\001 +4 0 0 0 0 14 16 0.0000 4 150 900 2175 675 xmlDoc\001 +4 0 0 0 0 14 16 0.0000 4 150 1050 675 3300 xmlAttr\001 +4 0 0 0 0 14 16 0.0000 4 135 1200 3225 825 DOCUMENT\001 +4 0 0 0 0 0 16 0.0000 4 150 390 3375 1650 root\001 +4 0 0 0 0 -1 20 0.0000 4 285 4770 5175 825 A DOM tree as built by the XML parser\001 +4 0 0 0 0 -1 20 0.0000 4 180 465 1050 6150 text\001 +4 0 0 0 0 -1 16 0.0000 4 225 990 2250 3000 properties\001 +4 0 0 0 0 -1 16 0.0000 4 150 720 1800 5475 content\001 diff --git a/doc/structure.gif b/doc/structure.gif new file mode 100644 index 00000000..6711480b Binary files /dev/null and b/doc/structure.gif differ diff --git a/doc/xml.html b/doc/xml.html new file mode 100644 index 00000000..d0f57a4c --- /dev/null +++ b/doc/xml.html @@ -0,0 +1,78 @@ + + + +No title + + + + +

The XML library for Gnome

+

+This document describes the XML library +provideed in the Gnome framework. XML is a +standard to build tag based structured documents. The internal document +repesentation is as close as possible to the DOM interfaces.

+ +

xml

+

+XML is a standard for markup based structured documents, here is an +example:

+
<?xml version="1.0"?>
+<EXAMPLE prop1="gnome is great" prop2="&linux; too">
+  <head>
+   <title>Welcome to Gnome</title>
+  </head>
+  <chapter>
+   <title>The Linux adventure</title>
+   <p>bla bla bla ...</p>
+   <image href="linus.gif"/>
+   <p>...</p>
+  </chapter>
+</EXAMPLE>
+

+

+ +

Invoking the parser

+ +

The tree output

+

+The parser returns a tree built during the document analysis. The value +returned is an xmlDocPtr (i.e. a pointer to an +xmlDoc structure). This structure contains informations like +the file name, the document type, and a root pointer which +is the root of the document (or more exactly the first child under the root +which is the document). The tree is made of xmlNodes, chained +in double linked lists of siblings and with childs<->parent relationship. +An xmlNode can also carry properties (a chain of xmlAttr structures). An +attribute may have a value which is a list of TEXT or ENTITY_REF nodes.

+

+Here is an example (erroneous w.r.t. the XML spec since there should be only +one ELEMENT under the root):

+

+ structure.gif

+

+

+ +

Modifying the tree

+ +

Saving a tree

+ +

DOM interfaces

+

+DOM stands for the Document Object +Model this is an API for accessing XML or HTML structured documents. +Native support for DOM in Gnome is on the way (module gnome-dom), and it will +be based on gnome-xml. DOM defiles a set of IDL (or Java) interfaces allowing +to traverse and manipulate a document. The DOM library will allow accessing +and modifying "live" documents presents on other programs like this:

+

+ DOM.gif

+

+This should help greatly doing things like modifying a gnumeric spreadsheet +embedded in a GWP document for example.

+

+

+ + diff --git a/encoding.c b/encoding.c index 02ff02af..77534193 100644 --- a/encoding.c +++ b/encoding.c @@ -77,7 +77,7 @@ UTF8Toisolat1(unsigned char* out, int outlen, unsigned char* in, int inlen) unsigned char* outstart= out; unsigned char* outend= out+outlen; unsigned char* inend= in+inlen; - unsigned char c, d; + unsigned char c; while (in < inend) { c= *in++; diff --git a/entities.c b/entities.c index 5a788e61..351746ce 100644 --- a/entities.c +++ b/entities.c @@ -143,6 +143,29 @@ void xmlInitializePredefinedEntities(void) { } } +/** + * xmlGetPredefinedEntity: + * @name: the entity name + * + * Check whether this name is an predefined entity. + * + * return values: NULL if not, othervise the entity + */ +xmlEntityPtr +xmlGetPredefinedEntity(const CHAR *name) { + int i; + xmlEntityPtr cur; + + if (xmlPredefinedEntities == NULL) + xmlInitializePredefinedEntities(); + for (i = 0;i < xmlPredefinedEntities->nb_entities;i++) { + cur = &xmlPredefinedEntities->table[i]; + if (!xmlStrcmp(cur->name, name)) return(cur); + } + return(NULL); +} + + /* * xmlAddDtdEntity : register a new entity for this DTD. diff --git a/entities.h b/entities.h index 0065245c..6f971c08 100644 --- a/entities.h +++ b/entities.h @@ -8,8 +8,8 @@ #ifndef __XML_ENTITIES_H__ #define __XML_ENTITIES_H__ -#include "parser.h" +#include "parser.h" #ifdef __cplusplus extern "C" { @@ -48,6 +48,7 @@ typedef struct xmlEntitiesTable { xmlEntityPtr table; /* the table of entities */ } xmlEntitiesTable, *xmlEntitiesTablePtr; + /* * External functions : */ @@ -56,12 +57,15 @@ extern void xmlAddDocEntity(xmlDocPtr doc, const CHAR *name, int type, const CHAR *ExternalID, const CHAR *SystemID, CHAR *content); extern void xmlAddDtdEntity(xmlDocPtr doc, const CHAR *name, int type, const CHAR *ExternalID, const CHAR *SystemID, CHAR *content); +extern xmlEntityPtr xmlGetPredefinedEntity(const CHAR *name); extern xmlEntityPtr xmlGetDocEntity(xmlDocPtr doc, const CHAR *name); extern xmlEntityPtr xmlGetDtdEntity(xmlDocPtr doc, const CHAR *name); extern CHAR *xmlEncodeEntities(xmlDocPtr doc, const CHAR *input); extern xmlEntitiesTablePtr xmlCreateEntitiesTable(void); extern void xmlFreeEntitiesTable(xmlEntitiesTablePtr table); extern void xmlDumpEntitiesTable(xmlEntitiesTablePtr table); +extern xmlParserInputPtr xmlNewEntityInputStream(xmlParserCtxtPtr ctxt, + xmlEntityPtr entity); #ifdef __cplusplus } diff --git a/include/libxml/entities.h b/include/libxml/entities.h index 0065245c..6f971c08 100644 --- a/include/libxml/entities.h +++ b/include/libxml/entities.h @@ -8,8 +8,8 @@ #ifndef __XML_ENTITIES_H__ #define __XML_ENTITIES_H__ -#include "parser.h" +#include "parser.h" #ifdef __cplusplus extern "C" { @@ -48,6 +48,7 @@ typedef struct xmlEntitiesTable { xmlEntityPtr table; /* the table of entities */ } xmlEntitiesTable, *xmlEntitiesTablePtr; + /* * External functions : */ @@ -56,12 +57,15 @@ extern void xmlAddDocEntity(xmlDocPtr doc, const CHAR *name, int type, const CHAR *ExternalID, const CHAR *SystemID, CHAR *content); extern void xmlAddDtdEntity(xmlDocPtr doc, const CHAR *name, int type, const CHAR *ExternalID, const CHAR *SystemID, CHAR *content); +extern xmlEntityPtr xmlGetPredefinedEntity(const CHAR *name); extern xmlEntityPtr xmlGetDocEntity(xmlDocPtr doc, const CHAR *name); extern xmlEntityPtr xmlGetDtdEntity(xmlDocPtr doc, const CHAR *name); extern CHAR *xmlEncodeEntities(xmlDocPtr doc, const CHAR *input); extern xmlEntitiesTablePtr xmlCreateEntitiesTable(void); extern void xmlFreeEntitiesTable(xmlEntitiesTablePtr table); extern void xmlDumpEntitiesTable(xmlEntitiesTablePtr table); +extern xmlParserInputPtr xmlNewEntityInputStream(xmlParserCtxtPtr ctxt, + xmlEntityPtr entity); #ifdef __cplusplus } diff --git a/include/libxml/parser.h b/include/libxml/parser.h index d0ca9580..51ba4670 100644 --- a/include/libxml/parser.h +++ b/include/libxml/parser.h @@ -128,6 +128,8 @@ typedef struct xmlSAXHandler { extern xmlSAXLocator xmlDefaultSAXLocator; extern xmlSAXHandler xmlDefaultSAXHandler; +#include "entities.h" + /* * Interfaces */ diff --git a/include/libxml/tree.h b/include/libxml/tree.h index 91677a61..2ebe2cdf 100644 --- a/include/libxml/tree.h +++ b/include/libxml/tree.h @@ -16,7 +16,30 @@ extern "C" { #endif /* - * Type definitions + * The different element types carried by an XML tree + * + * NOTE: This is synchronized with DOM Level1 values + * See http://www.w3.org/TR/REC-DOM-Level-1/ + */ +typedef enum { + XML_ELEMENT_NODE= 1, + XML_ATTRIBUTE_NODE= 2, + XML_TEXT_NODE= 3, + XML_CDATA_SECTION_NODE= 4, + XML_ENTITY_REF_NODE= 5, + XML_ENTITY_NODE= 6, + XML_PI_NODE= 7, + XML_COMMENT_NODE= 8, + XML_DOCUMENT_NODE= 9, + XML_DOCUMENT_TYPE_NODE= 10, + XML_DOCUMENT_FRAG_NODE= 11, + XML_NOTATION_NODE= 12 +} xmlElementType; + +/* + * Currently we use only 8bit chars internal representation, but + * the parser is not tied to that, just define UNICODE to switch to + * a 16 bits representation. */ #ifdef UNICODE typedef unsigned short CHAR; @@ -84,37 +107,22 @@ typedef struct xmlAttr { void *_private; /* for Corba, must be first ! */ void *vepv; /* for Corba, must be next ! */ #endif - int type; /* XML_ATTRIBUTE_NODE, must be third ! */ + xmlElementType type; /* XML_ATTRIBUTE_NODE, must be third ! */ struct xmlNode *node; /* attr->node link */ struct xmlAttr *next; /* parent->childs link */ const CHAR *name; /* the name of the property */ - const CHAR *value; /* the value of the property */ + struct xmlNode *val; /* the value of the property */ } xmlAttr, *xmlAttrPtr; /* * A node in an XML tree. - * NOTE: This is synchronized with DOM Level1 values - * See http://www.w3.org/TR/REC-DOM-Level-1/ */ -#define XML_ELEMENT_NODE 1 -#define XML_ATTRIBUTE_NODE 2 -#define XML_TEXT_NODE 3 -#define XML_CDATA_SECTION_NODE 4 -#define XML_ENTITY_REF_NODE 5 -#define XML_ENTITY_NODE 6 -#define XML_PI_NODE 7 -#define XML_COMMENT_NODE 8 -#define XML_DOCUMENT_NODE 9 -#define XML_DOCUMENT_TYPE_NODE 10 -#define XML_DOCUMENT_FRAG_NODE 11 -#define XML_NOTATION_NODE 12 - typedef struct xmlNode { #ifndef XML_WITHOUT_CORBA void *_private; /* for Corba, must be first ! */ void *vepv; /* for Corba, must be next ! */ #endif - int type; /* type number in the DTD, must be third ! */ + xmlElementType type; /* type number in the DTD, must be third ! */ struct xmlDoc *doc; /* the containing document */ struct xmlNode *parent; /* child->parent link */ struct xmlNode *next; /* next sibling link */ @@ -135,7 +143,7 @@ typedef struct xmlDoc { void *_private; /* for Corba, must be first ! */ void *vepv; /* for Corba, must be next ! */ #endif - int type; /* XML_DOCUMENT_NODE, must be second ! */ + xmlElementType type; /* XML_DOCUMENT_NODE, must be second ! */ char *name; /* name/filename/URI of the document */ const CHAR *version; /* the XML version string */ const CHAR *encoding; /* encoding, if any */ @@ -165,22 +173,27 @@ extern xmlNsPtr xmlNewNs(xmlNodePtr node, const CHAR *href, const CHAR *AS); extern void xmlFreeNs(xmlNsPtr cur); extern xmlDocPtr xmlNewDoc(const CHAR *version); extern void xmlFreeDoc(xmlDocPtr cur); +extern xmlAttrPtr xmlNewDocProp(xmlDocPtr doc, const CHAR *name, + const CHAR *value); extern xmlAttrPtr xmlNewProp(xmlNodePtr node, const CHAR *name, const CHAR *value); extern xmlAttrPtr xmlSetProp(xmlNodePtr node, const CHAR *name, const CHAR *value); extern const CHAR *xmlGetProp(xmlNodePtr node, const CHAR *name); +extern xmlNodePtr xmlStringGetNodeList(xmlDocPtr doc, const CHAR *value); +extern CHAR *xmlNodeListGetString(xmlDocPtr doc, xmlNodePtr list, int inLine); extern void xmlFreePropList(xmlAttrPtr cur); extern void xmlFreeProp(xmlAttrPtr cur); extern xmlNodePtr xmlNewDocNode(xmlDocPtr doc, xmlNsPtr ns, const CHAR *name, CHAR *content); -extern xmlNodePtr xmlNewNode(xmlNsPtr ns, const CHAR *name, CHAR *content); +extern xmlNodePtr xmlNewNode(xmlNsPtr ns, const CHAR *name); extern xmlNodePtr xmlNewDocText(xmlDocPtr doc, const CHAR *content); extern xmlNodePtr xmlNewText(const CHAR *content); extern xmlNodePtr xmlNewDocTextLen(xmlDocPtr doc, const CHAR *content, int len); extern xmlNodePtr xmlNewTextLen(const CHAR *content, int len); extern xmlNodePtr xmlNewDocComment(xmlDocPtr doc, CHAR *content); extern xmlNodePtr xmlNewComment(CHAR *content); +extern xmlNodePtr xmlNewReference(xmlDocPtr doc, const CHAR *name); extern xmlNodePtr xmlAddChild(xmlNodePtr parent, xmlNodePtr cur); extern xmlNodePtr xmlGetLastChild(xmlNodePtr node); extern int xmlNodeIsText(xmlNodePtr node); diff --git a/parser.c b/parser.c index 299a09a8..47323e0d 100644 --- a/parser.c +++ b/parser.c @@ -58,7 +58,10 @@ int name##Push(xmlParserCtxtPtr ctxt, type value) { \ type name##Pop(xmlParserCtxtPtr ctxt) { \ if (ctxt->name##Nr <= 0) return(0); \ ctxt->name##Nr--; \ - ctxt->name = ctxt->name##Tab[ctxt->name##Nr - 1]; \ + if (ctxt->name##Nr > 0) \ + ctxt->name = ctxt->name##Tab[ctxt->name##Nr - 1]; \ + else \ + ctxt->name = NULL; \ return(ctxt->name); \ } \ @@ -123,31 +126,33 @@ void xmlPushInput(xmlParserCtxtPtr ctxt, xmlParserInputPtr input) { * @entity: an Entity pointer * * Create a new input stream based on a memory buffer. + * return vakues: the new input stream */ -void xmlNewEntityInputStream(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { +xmlParserInputPtr +xmlNewEntityInputStream(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { xmlParserInputPtr input; if (entity == NULL) { xmlParserError(ctxt, "internal: xmlNewEntityInputStream entity = NULL\n"); - return; + return(NULL); } if (entity->content == NULL) { xmlParserError(ctxt, "internal: xmlNewEntityInputStream entity->input = NULL\n"); - return; + return(NULL); } input = (xmlParserInputPtr) malloc(sizeof(xmlParserInput)); if (input == NULL) { xmlParserError(ctxt, "malloc: couldn't allocate a new input stream\n"); - return; + return(NULL); } input->filename = entity->SystemID; /* TODO !!! char <- CHAR */ input->base = entity->content; input->cur = entity->content; input->line = 1; input->col = 1; - xmlPushInput(ctxt, input); + return(input); } /* @@ -876,6 +881,7 @@ static int areBlanks(xmlParserCtxtPtr ctxt, const CHAR *str, int len) { void xmlHandleEntity(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { int len; + xmlParserInputPtr input; if (entity->content == NULL) { xmlParserError(ctxt, "xmlHandleEntity %s: content == NULL\n", @@ -888,7 +894,8 @@ void xmlHandleEntity(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { /* * Redefine its content as an input stream. */ - xmlNewEntityInputStream(ctxt, entity); + input = xmlNewEntityInputStream(ctxt, entity); + xmlPushInput(ctxt, input); return; handle_as_char: @@ -904,8 +911,8 @@ handle_as_char: * Forward definition for recusive behaviour. */ xmlNodePtr xmlParseElement(xmlParserCtxtPtr ctxt); -CHAR *xmlParsePEReference(xmlParserCtxtPtr ctxt, int inLine); -CHAR *xmlParseReference(xmlParserCtxtPtr ctxt, int inLine); +CHAR *xmlParsePEReference(xmlParserCtxtPtr ctxt); +CHAR *xmlParseReference(xmlParserCtxtPtr ctxt); /************************************************************************ * * @@ -1231,13 +1238,22 @@ CHAR *xmlParseEntityValue(xmlParserCtxtPtr ctxt) { while ((IS_CHAR(CUR)) && (CUR != '"')) { if (CUR == '%') { ret = xmlStrncat(ret, q, CUR_PTR - q); - cur = xmlParsePEReference(ctxt, 1); + cur = xmlParsePEReference(ctxt); ret = xmlStrcat(ret, cur); q = CUR_PTR; } else if (CUR == '&') { ret = xmlStrncat(ret, q, CUR_PTR - q); - cur = xmlParseReference(ctxt, 1); - ret = xmlStrcat(ret, cur); + cur = xmlParseReference(ctxt); + if (cur != NULL) { + CHAR buf[2]; + buf[0] = '&'; + buf[1] = 0; + ret = xmlStrncat(ret, buf, 1); + ret = xmlStrcat(ret, cur); + buf[0] = ';'; + buf[1] = 0; + ret = xmlStrncat(ret, buf, 1); + } q = CUR_PTR; } else NEXT; @@ -1254,13 +1270,22 @@ CHAR *xmlParseEntityValue(xmlParserCtxtPtr ctxt) { while ((IS_CHAR(CUR)) && (CUR != '\'')) { if (CUR == '%') { ret = xmlStrncat(ret, q, CUR_PTR - q); - cur = xmlParsePEReference(ctxt, 1); + cur = xmlParsePEReference(ctxt); ret = xmlStrcat(ret, cur); q = CUR_PTR; } else if (CUR == '&') { ret = xmlStrncat(ret, q, CUR_PTR - q); - cur = xmlParseReference(ctxt, 1); - ret = xmlStrcat(ret, cur); + cur = xmlParseReference(ctxt); + if (cur != NULL) { + CHAR buf[2]; + buf[0] = '&'; + buf[1] = 0; + ret = xmlStrncat(ret, buf, 1); + ret = xmlStrcat(ret, cur); + buf[0] = ';'; + buf[1] = 0; + ret = xmlStrncat(ret, buf, 1); + } q = CUR_PTR; } else NEXT; @@ -1300,11 +1325,32 @@ CHAR *xmlParseAttValue(xmlParserCtxtPtr ctxt) { while ((IS_CHAR(CUR)) && (CUR != '"')) { if (CUR == '&') { ret = xmlStrncat(ret, q, CUR_PTR - q); - cur = xmlParseReference(ctxt, 1); - ret = xmlStrcat(ret, cur); + cur = xmlParseReference(ctxt); + if (cur != NULL) { + /* + * Special case for '&', we don't want to + * resolve it here since it will break later + * when searching entities in the string. + */ + if ((cur[0] == '&') && (cur[1] == 0)) { + CHAR buf[6] = { '&', 'a', 'm', 'p', ';', 0 }; + ret = xmlStrncat(ret, buf, 5); + } else + ret = xmlStrcat(ret, cur); + free(cur); + } q = CUR_PTR; } else NEXT; + /* + * Pop out finished entity references. + */ + while ((CUR == 0) && (ctxt->inputNr > 1)) { + if (CUR_PTR != q) + ret = xmlStrncat(ret, q, CUR_PTR - q); + xmlPopInput(ctxt); + q = CUR_PTR; + } } if (!IS_CHAR(CUR)) { xmlParserError(ctxt, "Unfinished AttValue\n"); @@ -1318,11 +1364,32 @@ CHAR *xmlParseAttValue(xmlParserCtxtPtr ctxt) { while ((IS_CHAR(CUR)) && (CUR != '\'')) { if (CUR == '&') { ret = xmlStrncat(ret, q, CUR_PTR - q); - cur = xmlParseReference(ctxt, 1); - ret = xmlStrcat(ret, cur); + cur = xmlParseReference(ctxt); + if (cur != NULL) { + /* + * Special case for '&', we don't want to + * resolve it here since it will break later + * when searching entities in the string. + */ + if ((cur[0] == '&') && (cur[1] == 0)) { + CHAR buf[6] = { '&', 'a', 'm', 'p', ';', 0 }; + ret = xmlStrncat(ret, buf, 5); + } else + ret = xmlStrcat(ret, cur); + free(cur); + } q = CUR_PTR; } else NEXT; + /* + * Pop out finished entity references. + */ + while ((CUR == 0) && (ctxt->inputNr > 1)) { + if (CUR_PTR != q) + ret = xmlStrncat(ret, q, CUR_PTR - q); + xmlPopInput(ctxt); + q = CUR_PTR; + } } if (!IS_CHAR(CUR)) { xmlParserError(ctxt, "Unfinished AttValue\n"); @@ -2060,7 +2127,6 @@ void xmlParseMarkupDecl(xmlParserCtxtPtr ctxt) { /** * xmlParseCharRef: * @ctxt: an XML parser context - * @inLine: handle it as inline or pass it to SAX as chars ? * * parse Reference declarations * @@ -2068,7 +2134,7 @@ void xmlParseMarkupDecl(xmlParserCtxtPtr ctxt) { * '&#x' [0-9a-fA-F]+ ';' * return values: the value parsed */ -CHAR *xmlParseCharRef(xmlParserCtxtPtr ctxt, int inLine) { +CHAR *xmlParseCharRef(xmlParserCtxtPtr ctxt) { int val = 0; CHAR buf[2]; @@ -2114,10 +2180,7 @@ CHAR *xmlParseCharRef(xmlParserCtxtPtr ctxt, int inLine) { if (IS_CHAR(val)) { buf[0] = (CHAR) val; buf[1] = 0; - if (inLine) - return(xmlStrndup(buf, 1)); - else if (ctxt->sax != NULL) - ctxt->sax->characters(ctxt, buf, 0, 1); + return(xmlStrndup(buf, 1)); } else { xmlParserError(ctxt, "xmlParseCharRef: invalid value"); } @@ -2127,18 +2190,19 @@ CHAR *xmlParseCharRef(xmlParserCtxtPtr ctxt, int inLine) { /** * xmlParseEntityRef: * @ctxt: an XML parser context - * @inLine: handle it as inline or pass it to SAX as chars ? * * parse ENTITY references declarations * * [68] EntityRef ::= '&' Name ';' - * return values: the entity content, or NULL if directly handled (inLine == 0) + * return values: the entity ref string or NULL if directly as input stream. */ -CHAR *xmlParseEntityRef(xmlParserCtxtPtr ctxt, int inLine) { +CHAR *xmlParseEntityRef(xmlParserCtxtPtr ctxt) { CHAR *ret = NULL; + const CHAR *q; CHAR *name; - xmlEntityPtr entity; + xmlParserInputPtr input = NULL; + q = CUR_PTR; if (CUR == '&') { NEXT; name = xmlParseName(ctxt); @@ -2147,40 +2211,18 @@ CHAR *xmlParseEntityRef(xmlParserCtxtPtr ctxt, int inLine) { } else { if (CUR == ';') { NEXT; - entity = xmlGetDocEntity(ctxt->doc, name); - if (entity == NULL) { - /* TODO !!! Create a reference ! */ - xmlParserWarning(ctxt, - "xmlParseEntityRef: &%s; not found\n", name); - } /* - * If we can get the content, push the entity content - * as the next input stream. + * We parsed the entity reference correctly, call SAX + * interface for the proper behaviour: + * - get a new input stream + * - or keep the reference inline */ + if (ctxt->sax) + input = ctxt->sax->resolveEntity(ctxt, NULL, name); + if (input != NULL) + xmlPushInput(ctxt, input); else { - switch (entity->type) { - case XML_INTERNAL_PARAMETER_ENTITY: - case XML_EXTERNAL_PARAMETER_ENTITY: - xmlParserError(ctxt, - "internal: xmlGetDtdEntity returned a general entity\n"); - break; - case XML_INTERNAL_GENERAL_ENTITY: - if (inLine) - ret = entity->content; - else - xmlHandleEntity(ctxt, entity); - break; - case XML_EXTERNAL_GENERAL_PARSED_ENTITY: - case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: - xmlParserWarning(ctxt, - "xmlParseEntityRef: external entity &%s; not supported\n", - name); - break; - default: - xmlParserError(ctxt, - "internal: xmlParseEntityRef: unknown entity type %d\n", - entity->type); - } + ret = xmlStrndup(q, CUR_PTR - q); } } else { char cst[2] = { '&', 0 }; @@ -2198,18 +2240,18 @@ CHAR *xmlParseEntityRef(xmlParserCtxtPtr ctxt, int inLine) { /** * xmlParseReference: * @ctxt: an XML parser context - * @inLine: handle it as inline or pass it to SAX as chars ? * * parse Reference declarations * * [67] Reference ::= EntityRef | CharRef - * return values: the entity content or NULL is handled directly + * return values: the entity string or NULL if handled directly by pushing + * the entity value as the input. */ -CHAR *xmlParseReference(xmlParserCtxtPtr ctxt, int inLine) { +CHAR *xmlParseReference(xmlParserCtxtPtr ctxt) { if ((CUR == '&') && (NXT(1) == '#')) { - return(xmlParseCharRef(ctxt, inLine)); + return(xmlParseCharRef(ctxt)); } else if (CUR == '&') { - return(xmlParseEntityRef(ctxt, inLine)); + return(xmlParseEntityRef(ctxt)); } return(NULL); } @@ -2217,17 +2259,17 @@ CHAR *xmlParseReference(xmlParserCtxtPtr ctxt, int inLine) { /** * xmlParsePEReference: * @ctxt: an XML parser context - * @inLine: handle it as inline or pass it to SAX as chars ? * * parse PEReference declarations * * [69] PEReference ::= '%' Name ';' - * return values: the entity content or NULL if handled differently. + * return values: the entity content or NULL if handled directly. */ -CHAR *xmlParsePEReference(xmlParserCtxtPtr ctxt, int inLine) { +CHAR *xmlParsePEReference(xmlParserCtxtPtr ctxt) { CHAR *ret = NULL; CHAR *name; xmlEntityPtr entity; + xmlParserInputPtr input; if (CUR == '%') { NEXT; @@ -2241,37 +2283,12 @@ CHAR *xmlParsePEReference(xmlParserCtxtPtr ctxt, int inLine) { if (entity == NULL) { xmlParserWarning(ctxt, "xmlParsePEReference: %%%s; not found\n"); - } - /* - * If we can get the content, push the entity content - * as the next input stream. - */ - else { - switch (entity->type) { - case XML_INTERNAL_PARAMETER_ENTITY: - if (inLine) - ret = entity->content; - else - xmlNewEntityInputStream(ctxt, entity); - break; - case XML_EXTERNAL_PARAMETER_ENTITY: - xmlParserWarning(ctxt, - "xmlParsePEReference: external entity %%%s; not supported\n"); - break; - case XML_INTERNAL_GENERAL_ENTITY: - case XML_EXTERNAL_GENERAL_PARSED_ENTITY: - case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: - xmlParserError(ctxt, - "internal: xmlGetDtdEntity returned a general entity\n"); - break; - default: - xmlParserError(ctxt, - "internal: xmlParsePEReference: unknown entity type %d\n", - entity->type); - } + } else { + input = xmlNewEntityInputStream(ctxt, entity); + xmlPushInput(ctxt, input); } } else { - char cst[2] = { '&', 0 }; + char cst[2] = { '%', 0 }; xmlParserError(ctxt, "xmlParsePEReference: expecting ';'\n"); ret = xmlStrndup(cst, 1); @@ -2339,7 +2356,7 @@ void xmlParseDocTypeDecl(xmlParserCtxtPtr ctxt) { SKIP_BLANKS; xmlParseMarkupDecl(ctxt); - xmlParsePEReference(ctxt, 0); + xmlParsePEReference(ctxt); if (CUR_PTR == check) { xmlParserError(ctxt, @@ -2387,15 +2404,16 @@ void xmlParseDocTypeDecl(xmlParserCtxtPtr ctxt) { * definition. */ -void xmlParseAttribute(xmlParserCtxtPtr ctxt, xmlNodePtr node) { - CHAR *name, *value = NULL; +xmlAttrPtr xmlParseAttribute(xmlParserCtxtPtr ctxt, xmlNodePtr node) { + CHAR *name; CHAR *ns; - xmlNodePtr val = NULL; + CHAR *value = NULL; + xmlAttrPtr ret; name = xmlNamespaceParseQName(ctxt, &ns); if (name == NULL) { xmlParserError(ctxt, "error parsing attribute name\n"); - return; + return(NULL); } /* @@ -2423,31 +2441,30 @@ void xmlParseAttribute(xmlParserCtxtPtr ctxt, xmlNodePtr node) { free(name); if (value != NULL) free(value); - return; + return(NULL); } if ((ns != NULL) && (ns[0] == 'x') && (ns[1] == 'm') && (ns[2] == 'l') && (ns[3] == 'n') && (ns[4] == 's') && (ns[5] == 0)) { /* a standard namespace definition */ xmlNewNs(node, value, name); + free(ns); if (name != NULL) free(name); if (value != NULL) free(value); - return; + return(NULL); } - /* - * Handle the attribute, this is done by the the SAX back end. The - * DOM default handling is to build the attribute content tree and - * link it to the element. - */ - if (name != NULL) { - if (ctxt->sax) - ctxt->sax->attribute(ctxt, name, value); - free(name); - } + ret = xmlNewProp(ctxt->node, name, NULL); + if (ret != NULL) + ret->val = xmlStringGetNodeList(ctxt->doc, value); + + if (ns != NULL) + free(ns); if (value != NULL) - free(value); + free(value); + free(name); + return(ret); } /** @@ -2474,11 +2491,13 @@ xmlNodePtr xmlParseStartTag(xmlParserCtxtPtr ctxt) { CHAR *namespace, *name; xmlNsPtr ns = NULL; xmlNodePtr ret = NULL; + xmlNodePtr parent = ctxt->node; if (CUR != '<') return(NULL); NEXT; name = xmlNamespaceParseQName(ctxt, &namespace); + if (name == NULL) return(NULL); /* * Note : the namespace resolution is deferred until the end of the @@ -2486,6 +2505,17 @@ xmlNodePtr xmlParseStartTag(xmlParserCtxtPtr ctxt) { * an attribute at this level. */ ret = xmlNewDocNode(ctxt->doc, ns, name, NULL); + if (ret == NULL) { + if (namespace != NULL) + free(namespace); + free(name); + return(NULL); + } + + /* + * We are parsing a new node. + */ + nodePush(ctxt, ret); /* * Now parse the attributes, it ends up with the ending @@ -2513,21 +2543,25 @@ xmlNodePtr xmlParseStartTag(xmlParserCtxtPtr ctxt) { */ ns = xmlSearchNs(ctxt->doc, ret, namespace); if (ns == NULL) /* ret still doesn't have a parent yet ! */ - ns = xmlSearchNs(ctxt->doc, ctxt->node, namespace); + ns = xmlSearchNs(ctxt->doc, parent, namespace); xmlSetNs(ret, ns); if (namespace != NULL) free(namespace); - /* - * We are parsing a new node. - */ - nodePush(ctxt, ret); - /* * SAX: Start of Element ! */ if (ctxt->sax != NULL) ctxt->sax->startElement(ctxt, name); + free(name); + + /* + * Link the child element + */ + if (ctxt->nodeNr < 2) return(ret); + parent = ctxt->nodeTab[ctxt->nodeNr - 2]; + if (parent != NULL) + xmlAddChild(parent, ctxt->node); return(ret); } @@ -2688,10 +2722,27 @@ void xmlParseContent(xmlParserCtxtPtr ctxt) { ret = xmlParseElement(ctxt); } /* - * Fifth case : a reference. + * Fifth case : a reference. If if has not been resolved, + * parsing returns it's Name, create the node */ else if (CUR == '&') { - xmlParseReference(ctxt, 0); + CHAR *val = xmlParseReference(ctxt); + if (val != NULL) { + if (val[0] != '&') { + /* + * inline predefined entity. + */ + if (ctxt->sax != NULL) + ctxt->sax->characters(ctxt, val, 0, xmlStrlen(val)); + } else { + /* + * user defined entity, create a node. + */ + ret = xmlNewReference(ctxt->doc, val); + xmlAddChild(ctxt->node, ret); + } + free(val); + } } /* * Last case, text. Note that References are handled directly. @@ -3266,6 +3317,11 @@ xmlDocPtr xmlParseDoc(CHAR *cur) { xmlParseDocument(ctxt); ret = ctxt->doc; + free(ctxt->nodeTab); + free(ctxt->inputTab); + if (input->filename != NULL) + free((char *)input->filename); + free(input); free(ctxt); return(ret); @@ -3381,6 +3437,11 @@ retry_bigger: ret = ctxt->doc; free(buffer); + free(ctxt->nodeTab); + free(ctxt->inputTab); + if (inputStream->filename != NULL) + free((char *)inputStream->filename); + free(inputStream); free(ctxt); return(ret); @@ -3415,6 +3476,8 @@ xmlDocPtr xmlParseMemory(char *buffer, int size) { input = (xmlParserInputPtr) malloc(sizeof(xmlParserInput)); if (input == NULL) { perror("malloc"); + free(ctxt->nodeTab); + free(ctxt->inputTab); free(ctxt); return(NULL); } @@ -3434,6 +3497,11 @@ xmlDocPtr xmlParseMemory(char *buffer, int size) { xmlParseDocument(ctxt); ret = ctxt->doc; + free(ctxt->nodeTab); + free(ctxt->inputTab); + if (input->filename != NULL) + free((char *)input->filename); + free(input); free(ctxt); return(ret); diff --git a/parser.h b/parser.h index d0ca9580..51ba4670 100644 --- a/parser.h +++ b/parser.h @@ -128,6 +128,8 @@ typedef struct xmlSAXHandler { extern xmlSAXLocator xmlDefaultSAXLocator; extern xmlSAXHandler xmlDefaultSAXHandler; +#include "entities.h" + /* * Interfaces */ diff --git a/result/ent1 b/result/ent1 index 14bf428f..04e280ec 100644 --- a/result/ent1 +++ b/result/ent1 @@ -3,5 +3,4 @@ ]> - Extensible Markup Language - + &xml; diff --git a/result/ent2 b/result/ent2 index 754f257f..670ce745 100644 --- a/result/ent2 +++ b/result/ent2 @@ -5,6 +5,5 @@ ]> - - This text is about XML, the Extensible Markup Language and this is an embedded - + &title; + This text is about XML, the &xml; and this is an embedded ℑ diff --git a/result/ent3 b/result/ent3 index b1c0b149..7fb4c7b8 100644 --- a/result/ent3 +++ b/result/ent3 @@ -2,6 +2,6 @@ ]> - + Test of entities in attributes. diff --git a/result/ent4 b/result/ent4 new file mode 100644 index 00000000..a92194cd --- /dev/null +++ b/result/ent4 @@ -0,0 +1,7 @@ + + +]> + + Test of &amp; behaviour a&b . + diff --git a/result/p3p b/result/p3p index 75eec90b..5ebda7a8 100644 --- a/result/p3p +++ b/result/p3p @@ -13,7 +13,7 @@ - + diff --git a/test/ent4 b/test/ent4 new file mode 100644 index 00000000..e668b404 --- /dev/null +++ b/test/ent4 @@ -0,0 +1,8 @@ + + +]> + + Test of &amp; behaviour a&b . + + diff --git a/tree.c b/tree.c index 0aeff3ce..202f0b83 100644 --- a/tree.c +++ b/tree.c @@ -345,6 +345,125 @@ void xmlFreeDoc(xmlDocPtr cur) { free(cur); } +/** + * xmlStringGetNodeList: + * @doc: the document + * @value: the value of the attribute + * + * Parse the value string and build the node list associated. Should + * produce a flat tree with only TEXTs and ENTITY_REFs. + * return values: a pointer to the first child + */ +xmlNodePtr xmlStringGetNodeList(xmlDocPtr doc, const CHAR *value) { + xmlNodePtr ret = NULL, last = NULL; + xmlNodePtr node; + CHAR *val; + const CHAR *cur = value; + const CHAR *q; + + if (value == NULL) return(NULL); + + q = cur; + while (*cur != 0) { + if (*cur == '&') { + if (cur != q) { + node = xmlNewTextLen(q, cur - q); + if (node == NULL) return(ret); + if (last == NULL) + last = ret = node; + else { + last->next = node; + last = node; + } + } + cur++; + q = cur; + while ((*cur != 0) && (*cur != ';')) cur++; + if (*cur == 0) { + fprintf(stderr, + "xmlStringGetNodeList: unterminated entity %30s\n", q); + return(ret); + } + if (cur != q) { + val = xmlStrndup(q, cur - q); + node = xmlNewReference(doc, val); + if (node == NULL) return(ret); + if (last == NULL) + last = ret = node; + else { + last->next = node; + last = node; + } + free(val); + } + cur++; + q = cur; + } else + cur++; + } + if (cur != q) { + node = xmlNewTextLen(q, cur - q); + if (node == NULL) return(ret); + if (last == NULL) + last = ret = node; + else { + last->next = node; + last = node; + } + } + return(ret); +} + +/** + * xmlNodeListGetString: + * @doc: the document + * @list: a Node list + * @inLine: should we replace entity contents or show their external form + * + * Returns the string equivalent to the text contained in the Node list + * made of TEXTs and ENTITY_REFs + * return values: a pointer to the string copy, the calller must free it. + */ +CHAR *xmlNodeListGetString(xmlDocPtr doc, xmlNodePtr list, int inLine) { + xmlNodePtr node = list; + CHAR *ret = NULL; + xmlEntityPtr ent; + + if (list == NULL) return(NULL); + + while (node != NULL) { + if (node->type == XML_TEXT_NODE) { + if (inLine) + ret = xmlStrcat(ret, node->content); + else + ret = xmlStrcat(ret, xmlEncodeEntities(doc, node->content)); + } else if (node->type == XML_ENTITY_REF_NODE) { + if (inLine) { + ent = xmlGetDocEntity(doc, node->name); + if (ent != NULL) + ret = xmlStrcat(ret, ent->content); + else + ret = xmlStrcat(ret, node->content); + } else { + CHAR buf[2]; + buf[0] = '&'; buf[1] = 0; + ret = xmlStrncat(ret, buf, 1); + ret = xmlStrcat(ret, node->name); + buf[0] = ';'; buf[1] = 0; + ret = xmlStrncat(ret, buf, 1); + } + } +#if 0 + else { + fprintf(stderr, "xmlGetNodeListString : invalide node type %d\n", + node->type); + } +#endif + node = node->next; + } + return(ret); +} + /** * xmlNewProp: * @node: the holding node @@ -375,9 +494,9 @@ xmlAttrPtr xmlNewProp(xmlNodePtr node, const CHAR *name, const CHAR *value) { cur->node = node; cur->name = xmlStrdup(name); if (value != NULL) - cur->value = xmlStrdup(value); + cur->val = xmlStringGetNodeList(node->doc, value); else - cur->value = NULL; + cur->val = NULL; #ifndef WITHOUT_CORBA cur->_private = NULL; cur->vepv = NULL; @@ -400,6 +519,48 @@ xmlAttrPtr xmlNewProp(xmlNodePtr node, const CHAR *name, const CHAR *value) { return(cur); } +/** + * xmlNewDocProp: + * @doc: the document + * @name: the name of the attribute + * @value: the value of the attribute + * + * Create a new property carried by a document. + * return values: a pointer to the attribute + */ +xmlAttrPtr xmlNewDocProp(xmlDocPtr doc, const CHAR *name, const CHAR *value) { + xmlAttrPtr cur; + + if (name == NULL) { + fprintf(stderr, "xmlNewProp : name == NULL\n"); + return(NULL); + } + + /* + * Allocate a new property and fill the fields. + */ + cur = (xmlAttrPtr) malloc(sizeof(xmlAttr)); + if (cur == NULL) { + fprintf(stderr, "xmlNewProp : malloc failed\n"); + return(NULL); + } + + cur->type = XML_ATTRIBUTE_NODE; + cur->node = NULL; + cur->name = xmlStrdup(name); + if (value != NULL) + cur->val = xmlStringGetNodeList(doc, value); + else + cur->val = NULL; +#ifndef WITHOUT_CORBA + cur->_private = NULL; + cur->vepv = NULL; +#endif + + cur->next = NULL; + return(cur); +} + /** * xmlFreePropList: * @cur: the first property in the list @@ -431,7 +592,7 @@ void xmlFreeProp(xmlAttrPtr cur) { return; } if (cur->name != NULL) free((char *) cur->name); - if (cur->value != NULL) free((char *) cur->value); + if (cur->val != NULL) xmlFreeNodeList(cur->val); memset(cur, -1, sizeof(xmlAttr)); free(cur); } @@ -443,9 +604,11 @@ void xmlFreeProp(xmlAttrPtr cur) { * @content: the text content if any * * Creation of a new node element. @ns and @content are optionnal (NULL). + * If content is non NULL, a child list containing the TEXTs and + * ENTITY_REFs node will be created. * return values: a pointer to the new node object. */ -xmlNodePtr xmlNewNode(xmlNsPtr ns, const CHAR *name, CHAR *content) { +xmlNodePtr xmlNewNode(xmlNsPtr ns, const CHAR *name) { xmlNodePtr cur; if (name == NULL) { @@ -473,14 +636,11 @@ xmlNodePtr xmlNewNode(xmlNsPtr ns, const CHAR *name, CHAR *content) { cur->name = xmlStrdup(name); cur->ns = ns; cur->nsDef = NULL; + cur->content = NULL; #ifndef WITHOUT_CORBA cur->_private = NULL; cur->vepv = NULL; #endif - if (content != NULL) - cur->content = xmlStrdup(content); - else - cur->content = NULL; return(cur); } @@ -499,8 +659,12 @@ xmlNodePtr xmlNewDocNode(xmlDocPtr doc, xmlNsPtr ns, const CHAR *name, CHAR *content) { xmlNodePtr cur; - cur = xmlNewNode(ns, name, content); - if (cur != NULL) cur->doc = doc; + cur = xmlNewNode(ns, name); + if (cur != NULL) { + cur->doc = doc; + if (content != NULL) + cur->childs = xmlStringGetNodeList(doc, content); + } return(cur); } @@ -542,6 +706,55 @@ xmlNodePtr xmlNewText(const CHAR *content) { return(cur); } +/** + * xmlNewReference: + * @doc: the document + * @name: the reference name, or the reference string with & and ; + * + * Creation of a new reference node. + * return values: a pointer to the new node object. + */ +xmlNodePtr xmlNewReference(xmlDocPtr doc, const CHAR *name) { + xmlNodePtr cur; + xmlEntityPtr ent; + + /* + * Allocate a new node and fill the fields. + */ + cur = (xmlNodePtr) malloc(sizeof(xmlNode)); + if (cur == NULL) { + fprintf(stderr, "xmlNewText : malloc failed\n"); + return(NULL); + } + + cur->type = XML_ENTITY_REF_NODE; + cur->doc = NULL; + cur->parent = NULL; + cur->next = NULL; + cur->prev = NULL; + cur->childs = NULL; + cur->properties = NULL; + if (name[0] == '&') { + int len; + name++; + len = xmlStrlen(name); + if (name[len - 1] == ';') + cur->name = xmlStrndup(name, len - 1); + else + cur->name = xmlStrndup(name, len); + } else + cur->name = xmlStrdup(name); + cur->ns = NULL; + cur->nsDef = NULL; + + ent = xmlGetDocEntity(doc, cur->name); + if (ent != NULL) + cur->content = ent->content; + else + cur->content = NULL; + return(cur); +} + /** * xmlNewDocText: * @doc: the document @@ -559,7 +772,7 @@ xmlNodePtr xmlNewDocText(xmlDocPtr doc, const CHAR *content) { } /** - * xmlNewText: + * xmlNewTextLen: * @content: the text content * @len: the text len. * @@ -676,7 +889,8 @@ xmlNodePtr xmlNewDocComment(xmlDocPtr doc, CHAR *content) { * * * Creation of a new child element, added at the end of @parent childs list. - * @ns and @content parameters are optionnal (NULL). + * @ns and @content parameters are optionnal (NULL). If content is non NULL, + * a child list containing the TEXTs and ENTITY_REFs node will be created. * return values: a pointer to the new node object. */ xmlNodePtr xmlNewChild(xmlNodePtr parent, xmlNsPtr ns, @@ -697,18 +911,15 @@ xmlNodePtr xmlNewChild(xmlNodePtr parent, xmlNsPtr ns, * Allocate a new node */ if (ns == NULL) - cur = xmlNewNode(parent->ns, name, content); + cur = xmlNewDocNode(parent->doc, parent->ns, name, content); else - cur = xmlNewNode(ns, name, content); + cur = xmlNewDocNode(parent->doc, ns, name, content); if (cur == NULL) return(NULL); /* * add the new element at the end of the childs list. */ - if (content == NULL) - cur->type = XML_ELEMENT_NODE; - else - cur->type = XML_TEXT_NODE; + cur->type = XML_ELEMENT_NODE; cur->parent = parent; cur->doc = parent->doc; if (parent->childs == NULL) { @@ -754,6 +965,23 @@ xmlNodePtr xmlAddChild(xmlNodePtr parent, xmlNodePtr cur) { */ cur->parent = parent; cur->doc = parent->doc; /* the parent may not be linked to a doc ! */ + /* + * Handle the case where parent->content != NULL, in that case it will + * create a intermediate TEXT node. + */ + if (parent->content != NULL) { + xmlNodePtr text; + + text = xmlNewDocText(parent->doc, parent->content); + if (text != NULL) { + text->next = parent->childs; + if (text->next != NULL) + text->next->prev = text; + parent->childs = text; + free(parent->content); + parent->content = NULL; + } + } if (parent->childs == NULL) { parent->childs = cur; } else { @@ -824,9 +1052,14 @@ void xmlFreeNode(xmlNodePtr cur) { fprintf(stderr, "xmlFreeNode : node == NULL\n"); return; } - if (cur->properties != NULL) xmlFreePropList(cur->properties); + cur->doc = NULL; + cur->parent = NULL; + cur->next = NULL; + cur->prev = NULL; if (cur->childs != NULL) xmlFreeNodeList(cur->childs); - if (cur->content != NULL) free(cur->content); + if (cur->properties != NULL) xmlFreePropList(cur->properties); + if (cur->type != XML_ENTITY_REF_NODE) + if (cur->content != NULL) free(cur->content); if (cur->name != NULL) free((char *) cur->name); if (cur->nsDef != NULL) xmlFreeNsList(cur->nsDef); memset(cur, -1, sizeof(xmlNode)); @@ -989,20 +1222,22 @@ xmlNsPtr xmlSearchNsByHref(xmlDocPtr doc, xmlNodePtr node, const CHAR *href) { * @name: the attribute name * * Search and get the value of an attribute associated to a node + * This does the entity substitution. * return values: the attribute value or NULL if not found. */ const CHAR *xmlGetProp(xmlNodePtr node, const CHAR *name) { xmlAttrPtr prop = node->properties; while (prop != NULL) { - if (!xmlStrcmp(prop->name, name)) return(prop->value); + if (!xmlStrcmp(prop->name, name)) + return(xmlNodeListGetString(node->doc, prop->val, 1)); prop = prop->next; } return(NULL); } /** - * xmlGetProp: + * xmlSetProp: * @node: the node * @name: the attribute name * @value: the attribute value @@ -1015,11 +1250,11 @@ xmlAttrPtr xmlSetProp(xmlNodePtr node, const CHAR *name, const CHAR *value) { while (prop != NULL) { if (!xmlStrcmp(prop->name, name)) { - if (prop->value != NULL) - free((char *) prop->value); - prop->value = NULL; + if (prop->val != NULL) + xmlFreeNode(prop->val); + prop->val = NULL; if (value != NULL) - prop->value = xmlStrdup(value); + prop->val = xmlStringGetNodeList(node->doc, value); return(prop); } prop = prop->next; @@ -1267,16 +1502,20 @@ static void xmlDtdDump(xmlDocPtr doc) { * Dump an XML attribute */ static void xmlAttrDump(xmlDocPtr doc, xmlAttrPtr cur) { + CHAR *value; + if (cur == NULL) { fprintf(stderr, "xmlAttrDump : property == NULL\n"); return; } xmlBufferWriteChar(" "); xmlBufferWriteCHAR(cur->name); - if (cur->value) { + value = xmlNodeListGetString(doc, cur->val, 0); + if (value) { xmlBufferWriteChar("=\""); - xmlBufferWriteCHAR(xmlEncodeEntities(doc, cur->value)); + xmlBufferWriteCHAR(value); xmlBufferWriteChar("\""); + free(value); } } @@ -1309,18 +1548,30 @@ static void xmlNodeDump(xmlDocPtr doc, xmlNodePtr cur, int level); * Dump an XML node list, recursive behaviour,children are printed too. */ static void xmlNodeListDump(xmlDocPtr doc, xmlNodePtr cur, int level) { + int needIndent = 0, i; + if (cur == NULL) { fprintf(stderr, "xmlNodeListDump : node == NULL\n"); return; } while (cur != NULL) { + if ((cur->type != XML_TEXT_NODE) && + (cur->type != XML_ENTITY_REF_NODE)) { + if (!needIndent) { + needIndent = 1; + xmlBufferWriteChar("\n"); + } + } xmlNodeDump(doc, cur, level); cur = cur->next; } + if ((xmlIndentTreeOutput) && (needIndent)) + for (i = 1;i < level;i++) + xmlBufferWriteChar(" "); } /** - * xmlNodeListDump: + * xmlNodeDump: * @doc: the document * @cur: the current node * @level: the imbrication level for indenting @@ -1347,6 +1598,12 @@ static void xmlNodeDump(xmlDocPtr doc, xmlNodePtr cur, int level) { } return; } + if (cur->type == XML_ENTITY_REF_NODE) { + xmlBufferWriteChar("&"); + xmlBufferWriteCHAR(cur->name); + xmlBufferWriteChar(";"); + return; + } if (xmlIndentTreeOutput) for (i = 0;i < level;i++) xmlBufferWriteChar(" "); @@ -1371,11 +1628,7 @@ static void xmlNodeDump(xmlDocPtr doc, xmlNodePtr cur, int level) { if (cur->content != NULL) xmlBufferWriteCHAR(xmlEncodeEntities(doc, cur->content)); if (cur->childs != NULL) { - xmlBufferWriteChar("\n"); xmlNodeListDump(doc, cur->childs, level + 1); - if (xmlIndentTreeOutput) - for (i = 0;i < level;i++) - xmlBufferWriteChar(" "); } xmlBufferWriteChar("ns != NULL) && (cur->ns->prefix != NULL)) { @@ -1531,7 +1784,7 @@ int xmlSaveFile(const char *filename, xmlDocPtr cur) { gzFile zoutput = NULL; char mode[15]; #endif - FILE *output; + FILE *output = NULL; int ret; #ifdef HAVE_ZLIB_H @@ -1584,7 +1837,7 @@ int main(void) { doc = xmlNewDoc("1.0"); ns1 = xmlNewNs(doc, "http://www.ietf.org/standards/dav/", "D"); ns2 = xmlNewNs(doc, "http://www.w3.com/standards/z39.50/", "Z"); - doc->root = xmlNewNode(ns1, "multistatus", NULL); + doc->root = xmlNewDocNode(doc, ns1, "multistatus", NULL); tree = xmlNewChild(doc->root, NULL, "response", NULL); subtree = xmlNewChild(tree, NULL, "prop", NULL); xmlNewChild(subtree, ns2, "Authors", NULL); diff --git a/tree.h b/tree.h index 91677a61..2ebe2cdf 100644 --- a/tree.h +++ b/tree.h @@ -16,7 +16,30 @@ extern "C" { #endif /* - * Type definitions + * The different element types carried by an XML tree + * + * NOTE: This is synchronized with DOM Level1 values + * See http://www.w3.org/TR/REC-DOM-Level-1/ + */ +typedef enum { + XML_ELEMENT_NODE= 1, + XML_ATTRIBUTE_NODE= 2, + XML_TEXT_NODE= 3, + XML_CDATA_SECTION_NODE= 4, + XML_ENTITY_REF_NODE= 5, + XML_ENTITY_NODE= 6, + XML_PI_NODE= 7, + XML_COMMENT_NODE= 8, + XML_DOCUMENT_NODE= 9, + XML_DOCUMENT_TYPE_NODE= 10, + XML_DOCUMENT_FRAG_NODE= 11, + XML_NOTATION_NODE= 12 +} xmlElementType; + +/* + * Currently we use only 8bit chars internal representation, but + * the parser is not tied to that, just define UNICODE to switch to + * a 16 bits representation. */ #ifdef UNICODE typedef unsigned short CHAR; @@ -84,37 +107,22 @@ typedef struct xmlAttr { void *_private; /* for Corba, must be first ! */ void *vepv; /* for Corba, must be next ! */ #endif - int type; /* XML_ATTRIBUTE_NODE, must be third ! */ + xmlElementType type; /* XML_ATTRIBUTE_NODE, must be third ! */ struct xmlNode *node; /* attr->node link */ struct xmlAttr *next; /* parent->childs link */ const CHAR *name; /* the name of the property */ - const CHAR *value; /* the value of the property */ + struct xmlNode *val; /* the value of the property */ } xmlAttr, *xmlAttrPtr; /* * A node in an XML tree. - * NOTE: This is synchronized with DOM Level1 values - * See http://www.w3.org/TR/REC-DOM-Level-1/ */ -#define XML_ELEMENT_NODE 1 -#define XML_ATTRIBUTE_NODE 2 -#define XML_TEXT_NODE 3 -#define XML_CDATA_SECTION_NODE 4 -#define XML_ENTITY_REF_NODE 5 -#define XML_ENTITY_NODE 6 -#define XML_PI_NODE 7 -#define XML_COMMENT_NODE 8 -#define XML_DOCUMENT_NODE 9 -#define XML_DOCUMENT_TYPE_NODE 10 -#define XML_DOCUMENT_FRAG_NODE 11 -#define XML_NOTATION_NODE 12 - typedef struct xmlNode { #ifndef XML_WITHOUT_CORBA void *_private; /* for Corba, must be first ! */ void *vepv; /* for Corba, must be next ! */ #endif - int type; /* type number in the DTD, must be third ! */ + xmlElementType type; /* type number in the DTD, must be third ! */ struct xmlDoc *doc; /* the containing document */ struct xmlNode *parent; /* child->parent link */ struct xmlNode *next; /* next sibling link */ @@ -135,7 +143,7 @@ typedef struct xmlDoc { void *_private; /* for Corba, must be first ! */ void *vepv; /* for Corba, must be next ! */ #endif - int type; /* XML_DOCUMENT_NODE, must be second ! */ + xmlElementType type; /* XML_DOCUMENT_NODE, must be second ! */ char *name; /* name/filename/URI of the document */ const CHAR *version; /* the XML version string */ const CHAR *encoding; /* encoding, if any */ @@ -165,22 +173,27 @@ extern xmlNsPtr xmlNewNs(xmlNodePtr node, const CHAR *href, const CHAR *AS); extern void xmlFreeNs(xmlNsPtr cur); extern xmlDocPtr xmlNewDoc(const CHAR *version); extern void xmlFreeDoc(xmlDocPtr cur); +extern xmlAttrPtr xmlNewDocProp(xmlDocPtr doc, const CHAR *name, + const CHAR *value); extern xmlAttrPtr xmlNewProp(xmlNodePtr node, const CHAR *name, const CHAR *value); extern xmlAttrPtr xmlSetProp(xmlNodePtr node, const CHAR *name, const CHAR *value); extern const CHAR *xmlGetProp(xmlNodePtr node, const CHAR *name); +extern xmlNodePtr xmlStringGetNodeList(xmlDocPtr doc, const CHAR *value); +extern CHAR *xmlNodeListGetString(xmlDocPtr doc, xmlNodePtr list, int inLine); extern void xmlFreePropList(xmlAttrPtr cur); extern void xmlFreeProp(xmlAttrPtr cur); extern xmlNodePtr xmlNewDocNode(xmlDocPtr doc, xmlNsPtr ns, const CHAR *name, CHAR *content); -extern xmlNodePtr xmlNewNode(xmlNsPtr ns, const CHAR *name, CHAR *content); +extern xmlNodePtr xmlNewNode(xmlNsPtr ns, const CHAR *name); extern xmlNodePtr xmlNewDocText(xmlDocPtr doc, const CHAR *content); extern xmlNodePtr xmlNewText(const CHAR *content); extern xmlNodePtr xmlNewDocTextLen(xmlDocPtr doc, const CHAR *content, int len); extern xmlNodePtr xmlNewTextLen(const CHAR *content, int len); extern xmlNodePtr xmlNewDocComment(xmlDocPtr doc, CHAR *content); extern xmlNodePtr xmlNewComment(CHAR *content); +extern xmlNodePtr xmlNewReference(xmlDocPtr doc, const CHAR *name); extern xmlNodePtr xmlAddChild(xmlNodePtr parent, xmlNodePtr cur); extern xmlNodePtr xmlGetLastChild(xmlNodePtr node); extern int xmlNodeIsText(xmlNodePtr node);