[xml] python wrapper for document API (AND transformCtxt API)

[Nic James Ferrier <nferrier tapsellferrier co uk>]

This is my two recent areas of work combined.

My motivation for building this API was to allow me to identify what
transformation a particular load was occuring for and this patch
enables me to do that. That's why I've combined them... they actually
make sense (to me anyway) together.


It does the following:

- adds a function to create an xslt transformContext from python

- adds a function to apply a stylesheet with a user supplied
  transformContext

- adds a python doc loader which calls a registered python function
  with a URI, xpathParserContext and transformContext and accepts a
  document in return

- adds a function to set the doc loader to a python function

- adds comparison API for transformContext objects


The patch is not complete... but it is usable and I will complete it
by adding these functions:

- a free for transformContext objects

- a getter for the python doc loader function


There are some problems that I could use some help with:

- why is the doc loader context sometimes a stylesheet instead of a
  transformContext?

  can libxslt/libxslt/documents.c::xsltLoadStyleDocument be changed so
  that it creates a transformContext or something?

- when the doc comes back from the python doc loader function do I
  have to DECREF it in some way?

- if I uncomment the xmlFreeParserCtxt(pctxt) at the end of the
  pythonDocLoaderFuncWrapper I get complaints from libc about double
  free-ing:

    *** glibc detected *** double free or corruption (fasttop): 0x0819a7f8 ***
    Aborted

  I can't see why this is really... I've copied the bones of the
  function from the libxml2 entity loader solution and it doesn't seem
  to have a problem with double free-ing.

- why could I not get a static cmp function to work as with
  libxml_compareNodesEqual? 

  There seems to be some difference between the libxml generator and
  the libxslt one?


-- 
Nic Ferrier
http://www.tapsellferrier.co.uk   for all your tapsell ferrier needs

Only in ../pristine/libxslt-1.1.17/libexslt: exsltconfig.h
Only in ../pristine/libxslt-1.1.17/libxslt: xsltconfig.h
Only in ../pristine/libxslt-1.1.17/libxslt: xsltwin32config.h
Only in ../pristine/libxslt-1.1.17: libxslt.spec
diff -r -u ../pristine/libxslt-1.1.17/python/generator.py ./python/generator.py
--- ../pristine/libxslt-1.1.17/python/generator.py      2004-01-22 17:40:16.000000000 +0000
+++ ./python/generator.py       2006-09-07 00:24:31.000000000 +0100
@@ -564,6 +564,7 @@
 classes_ancestor = {
     "xpathContext" : "libxml2.xpathContext",
     "xpathParserContext" : "libxml2.xpathParserContext",
+    "transformCtxt": "transformCtxtBase",
 }
 classes_destructors = {
     "xpathContext" : "pass"
Only in ./python: generator.py~
diff -r -u ../pristine/libxslt-1.1.17/python/libxsl.py ./python/libxsl.py
--- ../pristine/libxslt-1.1.17/python/libxsl.py 2004-07-11 12:12:33.000000000 +0100
+++ ./python/libxsl.py  2006-09-07 00:46:18.000000000 +0100
@@ -56,6 +56,20 @@
         import libxsltmod
         import libxml2
 
+
+class transformCtxtBase:
+    def __init__(self, _obj=None):
+        if _obj != None: 
+            self._o = _obj;
+            return
+        self._o = None
+    def __eq__(self, other):
+        if self == None or other == None:
+            return 0
+        v = libxsltmod.xsltCompareTransformContextsEqual(self._o, other._o)
+        return v
+        
+
 class extensionModule:
     def _styleInit(self, style, URI):
         return self.styleInit(stylesheet(_obj=style), URI)
Only in ./python: libxsl.py~
Only in ../pristine/libxslt-1.1.17/python: libxslt-py.c
diff -r -u ../pristine/libxslt-1.1.17/python/libxslt-python-api.xml ./python/libxslt-python-api.xml
--- ../pristine/libxslt-1.1.17/python/libxslt-python-api.xml    2006-09-01 03:14:20.000000000 +0100
+++ ./python/libxslt-python-api.xml     2006-09-07 00:33:35.000000000 +0100
@@ -11,6 +11,31 @@
       <arg name='style' type='xsltStylesheetPtr' info='a parsed XSLT stylesheet'/>
       <arg name='result' type='xmlDocPtr' info='The result document'/>
     </function>
+    <function name='xsltSetLoaderFunc' file='python'>
+      <info>Set the function for controlling document loading</info>
+      <return type='long' info='0 or 1'/>
+      <arg name='loader' type='pythonObject' info='the loader function'/>
+    </function>
+    <function name='xsltNewTransformContext' file='python'>
+      <info>Create a new XSLT TransformContext</info>
+      <return type='xsltTransformContextPtr' info='an xslt TransformContext'/>
+      <arg name='style' type='xsltStylesheetPtr' info='a parsed XSLT stylesheet'/>
+      <arg name='doc' type='xmlDocPtr' info='the input document'/>
+    </function>
+    <function name='xsltCompareTransformContextsEqual' file='python'>
+      <info>Compare one transformCtxt with another</info>
+      <return type='int' info='1 in case of success, 0 or -1 in error' />
+      <arg name='transformCtxt' type='xsltTransformContextPtr' info='a parsed XSLT transformContext'/>
+      <arg name='other' type='xsltTransformContextPtr' info='a parsed XSLT transformContext'/>
+    </function>
+    <function name='xsltApplyStylesheetUser' file='python'>
+      <info>Apply the stylesheet to the document</info>
+      <return type='xmlDocPtr' info="the result document or NULL in case of error"/>
+      <arg name='style' type='xsltStylesheetPtr' info='a parsed XSLT stylesheet'/>
+      <arg name='doc' type='xmlDocPtr' info='a parsed XML document'/>
+      <arg name='params' type='pythonObject' info='the parameters dictionnary'/>
+      <arg name='transformCtxt' type='xsltTransformContextPtr' info='transformation context'/>
+    </function>
     <function name='xsltApplyStylesheet' file='python'>
       <info>Apply the stylesheet to the document</info>
       <return type='xmlDocPtr' info="the result document or NULL in case of error"/>
Only in ./python: libxslt-python-api.xml~
diff -r -u ../pristine/libxslt-1.1.17/python/libxslt.c ./python/libxslt.c
--- ../pristine/libxslt-1.1.17/python/libxslt.c 2004-07-02 14:49:07.000000000 +0100
+++ ./python/libxslt.c  2006-09-07 00:34:38.000000000 +0100
@@ -20,6 +20,8 @@
 #include "libxslt_wrap.h"
 #include "libxslt-py.h"
 
+#include <stdio.h>
+
 #if (defined(_MSC_VER) || defined(__MINGW32__)) && !defined(vsnprintf)
 #define vsnprintf(b,c,f,a) _vsnprintf(b,c,f,a)
 #elif defined(XSLT_NEED_TRIO)
@@ -55,6 +57,9 @@
     }
     ret = PyCObject_FromVoidPtrAndDesc((void *) style,
                                       (char *)"xsltStylesheetPtr", NULL);
+
+    // Py_AddAttr(ret, cmp_function_impl);
+
     return(ret);
 }
 
@@ -90,6 +95,26 @@
     return(ret);
 }
 
+PyObject *
+libxslt_xsltCompareTransformContextsEqual(PyObject *self ATTRIBUTE_UNUSED, PyObject *args) {
+    
+    PyObject *py_tctxt1, *py_tctxt2;
+    xsltTransformContextPtr tctxt1, tctxt2;
+
+    if (!PyArg_ParseTuple(args, (char *)"OO:compareTransformContextsEqual", 
+                          &py_tctxt1, &py_tctxt2))
+        return NULL;
+
+    tctxt1 = (xsltTransformContextPtr) PytransformCtxt_Get(py_tctxt1);
+    tctxt2 = (xsltTransformContextPtr) PytransformCtxt_Get(py_tctxt2);
+
+    if ( tctxt1 == tctxt2 )
+        return Py_BuildValue((char *)"i", 1);
+    else
+        return Py_BuildValue((char *)"i", 0);
+}
+
+
 /************************************************************************
  *                                                                     *
  *                     Extending the API                               *
@@ -423,6 +448,105 @@
     return(py_retval);
 }
 
+
+/************************************************************************
+ *                                                                     *
+ *                     Document loading front-ends                     *
+ *                                                                     *
+ ************************************************************************/
+
+static PyObject *pythonDocLoaderObject = NULL;
+
+static xmlDocPtr
+pythonDocLoaderFuncWrapper(const xmlChar * URI, xmlDictPtr dict, int options,
+                           void *ctxt ATTRIBUTE_UNUSED,
+                           xsltLoadType type ATTRIBUTE_UNUSED)
+{
+    xmlParserCtxtPtr pctxt;
+    xmlDocPtr doc;
+
+    pctxt = xmlNewParserCtxt();
+    if (pctxt == NULL)
+        return(NULL);
+    if ((dict != NULL) && (pctxt->dict != NULL)) {
+        xmlDictFree(pctxt->dict);
+       pctxt->dict = NULL;
+    }
+    if (dict != NULL) {
+       pctxt->dict = dict;
+       xmlDictReference(pctxt->dict);
+#ifdef WITH_XSLT_DEBUG
+       xsltGenericDebug(xsltGenericDebugContext,
+                     "Reusing dictionary for document\n");
+#endif
+    }
+    xmlCtxtUseOptions(pctxt, options);
+
+    // now pass to python: pctxt, uri, options, ctxt
+    // the ctxt should be the stylesheet allowing us to differentiate between transformations
+    if (pythonDocLoaderObject != NULL) {
+        xsltStylesheetPtr style;
+        PyObject *ctxtobj;
+        PyObject *pctxtobj;
+        PyObject *result;
+
+        style = (xsltStylesheetPtr) ctxt;
+        ctxtobj = libxslt_xsltStylesheetPtrWrap(ctxt);
+        pctxtobj = libxml_xmlParserCtxtPtrWrap(pctxt);
+
+        // For now just send parserContext and URL
+        result = PyObject_CallFunction(pythonDocLoaderObject, 
+                                       (char *) "(sOO)", URI, pctxtobj, ctxtobj);
+       Py_XDECREF(pctxtobj);
+
+        if (result != NULL) {
+            // The return value should be the document
+            // Should we test it somehow before getting the C object from it?
+            PyObject *py_doc = PyObject_GetAttrString(result, "_o");
+            doc = PyxmlNode_Get(py_doc);
+
+            // do we have to DECCREF the result??
+        }
+    }
+
+    if (pctxt->wellFormed) {
+        // xmlDocDump(stderr, doc);
+        ;
+    }
+    else {
+        if (doc != NULL) {
+            xmlFreeDoc(doc);
+        }
+        if (pctxt->myDoc != NULL) {
+            doc = NULL;
+            xmlFreeDoc(pctxt->myDoc);
+            pctxt->myDoc = NULL;
+        }
+    }
+    // xmlFreeParserCtxt(pctxt);   // libc complains about double free-ing with this line
+
+    return(doc);
+}
+
+
+PyObject *
+libxslt_xsltSetLoaderFunc(PyObject *self ATTRIBUTE_UNUSED, PyObject *args) {
+    PyObject *py_retval;
+    PyObject *loader;
+
+    if (!PyArg_ParseTuple(args, (char *)"O:libxslt_xsltSetLoaderFunc",
+               &loader))
+       return(NULL);
+
+    pythonDocLoaderObject = loader;
+    xsltSetLoaderFunc(pythonDocLoaderFuncWrapper);
+
+    py_retval = PyInt_FromLong(0);
+    return(py_retval);    
+}
+
+
+
 /************************************************************************
  *                                                                     *
  *                     Some customized front-ends                      *
@@ -430,6 +554,103 @@
  ************************************************************************/
 
 PyObject *
+libxslt_xsltNewTransformContext(PyObject *self ATTRIBUTE_UNUSED, PyObject *args) {
+    PyObject *py_retval;
+    PyObject *pyobj_style;
+    PyObject *pyobj_doc;
+    xsltStylesheetPtr style;
+    xmlDocPtr doc;
+    xsltTransformContextPtr c_retval;
+
+    if (!PyArg_ParseTuple(args, (char *) "OO:xsltNewTransformContext",
+                         &pyobj_style, &pyobj_doc))
+        return(NULL);
+
+    style = (xsltStylesheetPtr) Pystylesheet_Get(pyobj_style);
+    doc = (xmlDocPtr) PyxmlNode_Get(pyobj_doc);
+    
+    c_retval = xsltNewTransformContext(style, doc);
+    py_retval = libxslt_xsltTransformContextPtrWrap((xsltTransformContextPtr) c_retval);
+    return (py_retval);
+}
+
+PyObject *
+libxslt_xsltApplyStylesheetUser(PyObject *self ATTRIBUTE_UNUSED, PyObject *args) {
+    PyObject *py_retval;
+    xmlDocPtr c_retval;
+    xsltStylesheetPtr style;
+    PyObject *pyobj_style;
+    xmlDocPtr doc;
+    xsltTransformContextPtr transformCtxt;
+    PyObject *pyobj_doc;
+    PyObject *pyobj_params;
+    PyObject *pyobj_transformCtxt;
+    const char **params = NULL;
+    int len = 0, i = 0, j;
+    PyObject *name;
+    PyObject *value;
+
+    if (!PyArg_ParseTuple(args, (char *) "OOOO:xsltApplyStylesheetUser",
+                         &pyobj_style, &pyobj_doc, &pyobj_params, &pyobj_transformCtxt))
+        return(NULL);
+
+    if (pyobj_params != Py_None) {
+       if (PyDict_Check(pyobj_params)) {
+           len = PyDict_Size(pyobj_params);
+           if (len > 0) {
+               params = (const char **) xmlMalloc((len + 1) * 2 *
+                                                  sizeof(char *));
+               if (params == NULL) {
+                   printf("libxslt_xsltApplyStylesheet: out of memory\n");
+                   Py_INCREF(Py_None);
+                   return(Py_None);
+               }
+               j = 0;
+               while (PyDict_Next(pyobj_params, &i, &name, &value)) {
+                   const char *tmp;
+                   int size;
+
+                   tmp = PyString_AS_STRING(name);
+                   size = PyString_GET_SIZE(name);
+                   params[j * 2] = (char *) xmlCharStrndup(tmp, size);
+                   if (PyString_Check(value)) {
+                       tmp = PyString_AS_STRING(value);
+                       size = PyString_GET_SIZE(value);
+                       params[(j * 2) + 1] = (char *)
+                           xmlCharStrndup(tmp, size);
+                   } else {
+                       params[(j * 2) + 1] = NULL;
+                   }
+                   j = j + 1;
+               }
+               params[j * 2] = NULL;
+               params[(j * 2) + 1] = NULL;
+           }
+       } else {
+           printf("libxslt_xsltApplyStylesheet: parameters not a dict\n");
+           Py_INCREF(Py_None);
+           return(Py_None);
+       }
+    }
+    style = (xsltStylesheetPtr) Pystylesheet_Get(pyobj_style);
+    doc = (xmlDocPtr) PyxmlNode_Get(pyobj_doc);
+    transformCtxt = (xsltTransformContextPtr) PytransformCtxt_Get(pyobj_transformCtxt);
+
+    c_retval = xsltApplyStylesheetUser(style, doc, params, NULL, NULL, transformCtxt);
+    py_retval = libxml_xmlDocPtrWrap((xmlDocPtr) c_retval);
+    if (params != NULL) {
+       if (len > 0) {
+           for (i = 0;i < 2 * len;i++) {
+               if (params[i] != NULL)
+                   xmlFree((char *)params[i]);
+           }
+           xmlFree(params);
+       }
+    }
+    return(py_retval);
+}
+
+PyObject *
 libxslt_xsltApplyStylesheet(PyObject *self ATTRIBUTE_UNUSED, PyObject *args) {
     PyObject *py_retval;
     xmlDocPtr c_retval;
Only in ./python: libxslt.c~
Only in ./python/tests: loader.py
Only in ./python/tests: loader.py~