XML validation: Difference between revisions
Added Wren |
|||
Line 570: | Line 570: | ||
Element 'a': Element content is not allowed, because the type definition is simple.</pre> |
Element 'a': Element content is not allowed, because the type definition is simple.</pre> |
||
=={{header| |
=={{header|Phix}}== |
||
{{trans|C}} |
|||
Note that error handling has been delegated to within libxml.e, specifically |
|||
xmlSchemaNewParserCtxt() and xmlSchemaNewValidCtxt() assign an internal handler, |
|||
which resorts to xmlGetLastError() and therefore needs to use a bit of cffi, |
|||
that is rather than using the (odd-looking) error it is actually passed. |
|||
The libxml.e wrapper was penned specifically for this task and is just about as |
|||
bare-bones as it could ever possibly be, and win32-only, for now. |
|||
<!--<lang Phix>(notonline)--> |
|||
<span style="color: #000080;font-style:italic;">-- |
|||
-- demo\rosetta\Validate_XML.exw |
|||
-- ============================= |
|||
--</span> |
|||
<span style="color: #008080;">without</span> <span style="color: #008080;">js</span> |
|||
<span style="color: #7060A8;">requires</span><span style="color: #0000FF;">(</span><span style="color: #000000;">32</span><span style="color: #0000FF;">)</span> <span style="color: #000080;font-style:italic;">-- let me know if you can get this to work on 64bit</span> |
|||
<span style="color: #7060A8;">requires</span><span style="color: #0000FF;">(</span><span style="color: #004600;">WINDOWS</span><span style="color: #0000FF;">)</span> <span style="color: #000080;font-style:italic;">-- "" if you can get this to work on linux</span> |
|||
<span style="color: #008080;">constant</span> <span style="color: #000000;">dl</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">`Download rosetta\libxml\ from http://phix.x10.mx/pmwiki/pmwiki.php?n=Main.libxml`</span> |
|||
<span style="color: #7060A8;">assert</span><span style="color: #0000FF;">(</span><span style="color: #7060A8;">get_file_type</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"libxml"</span><span style="color: #0000FF;">)=</span><span style="color: #004600;">FILETYPE_DIRECTORY</span><span style="color: #0000FF;">,</span><span style="color: #000000;">dl</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #008080;">include</span> <span style="color: #000000;">libxml</span><span style="color: #0000FF;">\</span><span style="color: #000000;">libxml</span><span style="color: #0000FF;">.</span><span style="color: #000000;">e</span> |
|||
<span style="color: #008080;">constant</span> <span style="color: #000000;">XSDFileName</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">`libxml\shiporder.xsd`</span><span style="color: #0000FF;">,</span> <span style="color: #000080;font-style:italic;">-- (versions 2 & 3 also included in "")</span> |
|||
<span style="color: #000000;">XMLFileName</span> <span style="color: #0000FF;">=</span> <span style="color: #008000;">`libxml\shiporder.xml`</span> |
|||
<span style="color: #000000;">xmlLineNumbersDefault</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #004080;">atom</span> <span style="color: #000000;">pctxt</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">xmlSchemaNewParserCtxt</span><span style="color: #0000FF;">(</span><span style="color: #000000;">XSDFileName</span><span style="color: #0000FF;">),</span> |
|||
<span style="color: #000000;">schema</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">xmlSchemaParse</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pctxt</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #000000;">xmlSchemaFreeParserCtxt</span><span style="color: #0000FF;">(</span><span style="color: #000000;">pctxt</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #004080;">atom</span> <span style="color: #000000;">doc</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">xmlReadFile</span><span style="color: #0000FF;">(</span><span style="color: #000000;">XMLFileName</span><span style="color: #0000FF;">,</span> <span style="color: #004600;">NULL</span><span style="color: #0000FF;">,</span> <span style="color: #000000;">0</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #008080;">if</span> <span style="color: #000000;">doc</span><span style="color: #0000FF;">=</span><span style="color: #004600;">NULL</span> <span style="color: #008080;">then</span> |
|||
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">2</span><span style="color: #0000FF;">,</span> <span style="color: #008000;">"Could not parse %s\n"</span><span style="color: #0000FF;">,</span> <span style="color: #0000FF;">{</span><span style="color: #000000;">XMLFileName</span><span style="color: #0000FF;">})</span> |
|||
<span style="color: #008080;">else</span> |
|||
<span style="color: #004080;">atom</span> <span style="color: #000000;">vctxt</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">xmlSchemaNewValidCtxt</span><span style="color: #0000FF;">(</span><span style="color: #000000;">schema</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #004080;">integer</span> <span style="color: #000000;">ret</span> <span style="color: #0000FF;">=</span> <span style="color: #000000;">xmlSchemaValidateDoc</span><span style="color: #0000FF;">(</span><span style="color: #000000;">vctxt</span><span style="color: #0000FF;">,</span> <span style="color: #000000;">doc</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #008080;">if</span> <span style="color: #000000;">ret</span><span style="color: #0000FF;">=</span><span style="color: #000000;">0</span> <span style="color: #008080;">then</span> |
|||
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"%s validates\n"</span><span style="color: #0000FF;">,</span> <span style="color: #0000FF;">{</span><span style="color: #000000;">XMLFileName</span><span style="color: #0000FF;">})</span> |
|||
<span style="color: #008080;">elsif</span> <span style="color: #000000;">ret</span><span style="color: #0000FF;">></span><span style="color: #000000;">0</span> <span style="color: #008080;">then</span> |
|||
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"%s fails to validate\n"</span><span style="color: #0000FF;">,</span> <span style="color: #0000FF;">{</span><span style="color: #000000;">XMLFileName</span><span style="color: #0000FF;">})</span> |
|||
<span style="color: #008080;">else</span> |
|||
<span style="color: #7060A8;">printf</span><span style="color: #0000FF;">(</span><span style="color: #000000;">1</span><span style="color: #0000FF;">,</span><span style="color: #008000;">"%s validation generated an internal error\n"</span><span style="color: #0000FF;">,</span> <span style="color: #0000FF;">{</span><span style="color: #000000;">XMLFileName</span><span style="color: #0000FF;">})</span> |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
<span style="color: #000000;">xmlSchemaFreeValidCtxt</span><span style="color: #0000FF;">(</span><span style="color: #000000;">vctxt</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #000000;">xmlFreeDoc</span><span style="color: #0000FF;">(</span><span style="color: #000000;">doc</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
<span style="color: #008080;">if</span> <span style="color: #000000;">schema</span><span style="color: #0000FF;">!=</span><span style="color: #004600;">NULL</span> <span style="color: #008080;">then</span> |
|||
<span style="color: #000000;">xmlSchemaFree</span><span style="color: #0000FF;">(</span><span style="color: #000000;">schema</span><span style="color: #0000FF;">)</span> |
|||
<span style="color: #008080;">end</span> <span style="color: #008080;">if</span> |
|||
<span style="color: #000000;">xmlSchemaCleanupTypes</span><span style="color: #0000FF;">()</span> |
|||
<span style="color: #000000;">xmlCleanupParser</span><span style="color: #0000FF;">()</span> |
|||
<span style="color: #000000;">xmlMemoryDump</span><span style="color: #0000FF;">()</span> |
|||
<!--</lang>--> |
|||
{{out}} |
|||
<pre> |
|||
libxml\shiporder.xml validates |
|||
</pre> |
|||
Performing the same error handling check as Nim, ie changing orderperson to orderperson1 (twice) results in: |
|||
<pre> |
|||
Error/Warning in line 6 |
|||
Element 'orderperson1': This element is not expected. Expected is ( orderperson ). |
|||
libxml\shiporder.xml fails to validate |
|||
</pre> |
|||
All three formats of the xsd file as given on the W3 page give identical results, for both with and without that error. |
|||
=={{header|PHP}}== |
|||
<lang php> |
<lang php> |
||
libxml_use_internal_errors(true); |
libxml_use_internal_errors(true); |
||
Line 609: | Line 671: | ||
Done. |
Done. |
||
</pre> |
</pre> |
||
=={{header|Python}}== |
=={{header|Python}}== |
||
Revision as of 21:51, 20 December 2021
Given an XML document and an XSD schema definition validate that the document follows the schema described.
Sample XML and XSD for tests can be found on this W3 Schools page.
C
At the time of writing, the XML and XSD files at the URLs used in the other examples were inaccessible. The files from the W3 Schools page were used for tests. <lang C>
- include <libxml/xmlschemastypes.h>
int main(int argC, char** argV) { if (argC <= 2) { printf("Usage: %s <XML Document Name> <XSD Document Name>\n", argV[0]); return 0; }
xmlDocPtr doc; xmlSchemaPtr schema = NULL; xmlSchemaParserCtxtPtr ctxt; char *XMLFileName = argV[1]; char *XSDFileName = argV[2]; int ret;
xmlLineNumbersDefault(1);
ctxt = xmlSchemaNewParserCtxt(XSDFileName);
xmlSchemaSetParserErrors(ctxt, (xmlSchemaValidityErrorFunc) fprintf, (xmlSchemaValidityWarningFunc) fprintf, stderr); schema = xmlSchemaParse(ctxt); xmlSchemaFreeParserCtxt(ctxt);
doc = xmlReadFile(XMLFileName, NULL, 0);
if (doc == NULL){ fprintf(stderr, "Could not parse %s\n", XMLFileName); } else{ xmlSchemaValidCtxtPtr ctxt;
ctxt = xmlSchemaNewValidCtxt(schema); xmlSchemaSetValidErrors(ctxt, (xmlSchemaValidityErrorFunc) fprintf, (xmlSchemaValidityWarningFunc) fprintf, stderr); ret = xmlSchemaValidateDoc(ctxt, doc);
if (ret == 0){ printf("%s validates\n", XMLFileName); } else if (ret > 0){ printf("%s fails to validate\n", XMLFileName); } else{ printf("%s validation generated an internal error\n", XMLFileName); } xmlSchemaFreeValidCtxt(ctxt); xmlFreeDoc(doc); }
if(schema != NULL)
xmlSchemaFree(schema);
xmlSchemaCleanupTypes(); xmlCleanupParser(); xmlMemoryDump();
return 0; } </lang> Output, files used from the W3 Schools page :
C:\rosettaCode>xmlValidator.exe shiporder.xml shiporder.xsd shiporder.xml validates
C#
<lang csharp> using System; using System.Xml; using System.Xml.Schema; using System.IO;
public class Test { public static void Main() { // your code goes here XmlSchemaSet sc = new XmlSchemaSet(); sc.Add(null, "http://venus.eas.asu.edu/WSRepository/xml/Courses.xsd"); XmlReaderSettings settings = new XmlReaderSettings(); settings.ValidationType = ValidationType.Schema; settings.Schemas = sc; settings.ValidationEventHandler += new ValidationEventHandler(ValidationCallBack); // Create the XmlReader object. XmlReader reader = XmlReader.Create("http://venus.eas.asu.edu/WSRepository/xml/Courses.xml", settings); // Parse the file. while (reader.Read()); // will call event handler if invalid Console.WriteLine("The XML file is valid for the given xsd file"); }
// Display any validation errors. private static void ValidationCallBack(object sender, ValidationEventArgs e) { Console.WriteLine("Validation Error: {0}", e.Message); } } </lang>
F#
Using an inline stylesheet:
<lang fsharp>open System.Xml open System.Xml.Schema open System.IO
let xml = @"<root> <xs:schema id='an-element' targetNamespace='example' xmlns:mstns='example' xmlns='example' xmlns:xs='http://www.w3.org/2001/XMLSchema' attributeFormDefault='unqualified' elementFormDefault='qualified'>
<xs:element name='an-element'> <xs:complexType> <xs:sequence minOccurs='0' maxOccurs='unbounded'> <xs:element name='another-element' nillable='true'> <xs:complexType> <xs:simpleContent> <xs:extension base='xs:string'> <xs:attribute name='an-attribute' form='unqualified' type='xs:boolean' /> </xs:extension> </xs:simpleContent> </xs:complexType> </xs:element> </xs:sequence> </xs:complexType> </xs:element>
</xs:schema> <an-element xmlns='example'>
<another-element an-attribute='false'>...</another-element> <another-element an-attribute='wrong'>123</another-element>
</an-element> </root>"
let validationData withWarnings =
let errors = ref 0 let warnings = ref 0 fun input -> match input with | Some(msg, severity) -> if severity = XmlSeverityType.Error then errors := !errors + 1 printfn "Validation error: %s" msg elif withWarnings then warnings := !warnings + 1 printfn "Validation warning: %s" msg None | None -> if withWarnings then Some(dict[XmlSeverityType.Error, !errors; XmlSeverityType.Warning, !warnings]) else Some(dict[XmlSeverityType.Error, !errors])
[<EntryPoint>] let main argv =
let withWarnings = argv.Length > 0 && argv.[0] = "-w" let vData = validationData withWarnings let validationEvent = new ValidationEventHandler(fun _ e -> vData (Some(e.Message, e.Severity)) |> ignore) let settings = new XmlReaderSettings() settings.ValidationType <- ValidationType.Schema settings.ValidationEventHandler.AddHandler(validationEvent) settings.ValidationFlags <- settings.ValidationFlags ||| XmlSchemaValidationFlags.ProcessInlineSchema ||| XmlSchemaValidationFlags.ReportValidationWarnings let reader = XmlReader.Create(new StringReader(xml), settings); while reader.Read() do () printfn "%A" (Seq.toList (vData None).Value) 0
</lang>
- Output:
>RosettaCode Validation error: The 'an-attribute' element is invalid - The value 'wrong' is invalid according to its datatype 'http://www.w3.org/2001/XMLSchema:boolean' - The string 'wrong' is not a valid boolean value. [[Error, 1]] >RosettaCode -w Validation warning: Could not find schema information for the element 'root'. Validation error: The 'an-attribute' element is invalid - The value 'wrong' is invalid according to its datatype 'http://www.w3.org/2001/XMLSchema:boolean' - The string 'wrong' is not a valid boolean value. [[Error, 1]; [Warning, 1]]
Changing wrong
to a boolean, e. g. true
, The result (without -w) is
[[Error, 0]]
Go
This uses the w3schools test data linked to above.
<lang go>package main
import (
"fmt" "github.com/lestrrat-go/libxml2" "github.com/lestrrat-go/libxml2/xsd" "io/ioutil" "log" "os"
)
func check(err error) {
if err != nil { log.Fatal(err) }
}
func main() {
xsdfile := "shiporder.xsd" f, err := os.Open(xsdfile) check(err) defer f.Close()
buf, err := ioutil.ReadAll(f) check(err)
s, err := xsd.Parse(buf) check(err) defer s.Free()
xmlfile := "shiporder.xml" f2, err := os.Open(xmlfile) check(err) defer f2.Close()
buf2, err := ioutil.ReadAll(f2) check(err)
d, err := libxml2.Parse(buf2) check(err)
if err := s.Validate(d); err != nil { for _, e := range err.(xsd.SchemaValidationError).Errors() { log.Printf("error: %s", e.Error()) } return }
fmt.Println("Validation of", xmlfile, "against", xsdfile, "successful!")
}</lang>
- Output:
Validation of shiporder.xml against shiporder.xsd successful!
Groovy
Solution: <lang groovy>import static javax.xml.XMLConstants.W3C_XML_SCHEMA_NS_URI import javax.xml.transform.stream.StreamSource import javax.xml.validation.SchemaFactory import org.xml.sax.SAXParseException
def factory = SchemaFactory.newInstance(W3C_XML_SCHEMA_NS_URI) def validate = { schemaURL, docURL ->
try { factory.newSchema(schemaURL.toURL()).newValidator().validate(new StreamSource(docURL)) true } catch (SAXParseException e) { false }
}</lang>
Test: <lang groovy>def schemaLoc = "http://venus.eas.asu.edu/WSRepository/xml/Courses.xsd" def docLoc = "http://venus.eas.asu.edu/WSRepository/xml/Courses.xml" println "Document is ${validate(schemaLoc, docLoc)? 'valid' : 'invalid'}"</lang>
Java
<lang java>import static javax.xml.XMLConstants.W3C_XML_SCHEMA_NS_URI;
import java.net.MalformedURLException; import java.net.URL;
import javax.xml.transform.stream.StreamSource; import javax.xml.validation.SchemaFactory; import javax.xml.validation.Validator; import javax.xml.ws.Holder;
import org.xml.sax.ErrorHandler; import org.xml.sax.SAXException; import org.xml.sax.SAXParseException;
public class XmlValidation { public static void main(String... args) throws MalformedURLException { URL schemaLocation = new URL("http://venus.eas.asu.edu/WSRepository/xml/Courses.xsd"); URL documentLocation = new URL("http://venus.eas.asu.edu/WSRepository/xml/Courses.xml"); if (validate(schemaLocation, documentLocation)) { System.out.println("document is valid"); } else { System.out.println("document is invalid"); } }
// The least code you need for validation public static boolean minimalValidate(URL schemaLocation, URL documentLocation) { SchemaFactory factory = SchemaFactory.newInstance(W3C_XML_SCHEMA_NS_URI); try { Validator validator = factory.newSchema(schemaLocation).newValidator(); validator.validate(new StreamSource(documentLocation.toString())); return true; } catch (Exception e) { return false; } }
// A more complete validator public static boolean validate(URL schemaLocation, URL documentLocation) { SchemaFactory factory = SchemaFactory.newInstance(W3C_XML_SCHEMA_NS_URI); final Holder<Boolean> valid = new Holder<>(true); try { Validator validator = factory.newSchema(schemaLocation).newValidator(); // Get some better diagnostics out validator.setErrorHandler(new ErrorHandler(){ @Override public void warning(SAXParseException exception) { System.out.println("warning: " + exception.getMessage()); }
@Override public void error(SAXParseException exception) { System.out.println("error: " + exception.getMessage()); valid.value = false; }
@Override public void fatalError(SAXParseException exception) throws SAXException { System.out.println("fatal error: " + exception.getMessage()); throw exception; }}); validator.validate(new StreamSource(documentLocation.toString())); return valid.value; } catch (SAXException e) { // Already reported above return false; } catch (Exception e) { // If this is the only thing that throws, it's a gross error System.err.println(e); return false; } } }</lang>
Julia
<lang julia>using LightXML
const Xptr = LightXML.Xptr
function validate(url::String, schemafile::String)
ctxt = ccall((:xmlSchemaNewParserCtxt, LightXML.libxml2), Xptr, (Cstring,), schemafile) ctxt != C_NULL || throw(LightXML.XMLNoRootError()) schema = ccall((:xmlSchemaParse, LightXML.libxml2), Xptr, (Xptr,), ctxt) schema != C_NULL || throw(LightXML.XMLNoRootError()) ccall((:xmlSchemaFreeParserCtxt, LightXML.libxml2), Cvoid, (Xptr,), ctxt) ctxt = ccall((:xmlSchemaNewValidCtxt, LightXML.libxml2), Xptr, (Xptr,), schema) err = ccall((:xmlSchemaValidateFile, LightXML.libxml2), Cint, (Ptr{LightXML.xmlBuffer}, Cstring), ctxt, url) return err == 0 ? true : false
end
function xsdvalidatexml()
if length(ARGS) != 2 println(" Usage: julia ", PROGRAM_FILE, ", xmlfilename xsdfilename") elseif validate(ARGS[1], ARGS[2]) println("File ", ARGS[1], " validates as correct XML using the XSD file ", ARGS[2], ".") else println("File ", ARGS[1]. "does not validate.") end
end
xsdvalidatexml() </lang>
Kotlin
Assuming that libxml2 is already installed on your system in the default location(s), you first need to build libxml_schemas.klib using the following .def file and the cinterop tool:
// libxml_schemas.def headers = /usr/include/libxml2/libxml/xmlschemastypes.h compilerOpts = -I/usr/include/libxml2 linkerOpts = -L/usr/lib/x86_64-linux-gnu -lxml2
Next, you need to compile the following Kotlin program, linking against libxml_schemas.klib. <lang scala>// Kotlin Native v0.6
import kotlinx.cinterop.* import platform.posix.* import libxml_schemas.*
fun err(ctx: COpaquePointer?, msg: CPointer<ByteVar>?, extra: CPointer<ByteVar>?) {
val fp = ctx?.reinterpret<FILE>() fprintf(fp, msg?.toKString(), extra?.toKString())
}
fun warn(ctx: COpaquePointer?, msg: CPointer<ByteVar>?, extra: CPointer<ByteVar>?) {
err(ctx, msg, extra)
}
fun main(args: Array<String>) {
if (args.size != 2) { println("You need to pass exactly 2 command line arguments, namely:") println(" <XML Document Name> <XSD Document Name>") return }
val xmlFileName = args[0] val xsdFileName = args[1] xmlLineNumbersDefault(1) val ctxt = xmlSchemaNewParserCtxt(xsdFileName)
xmlSchemaSetParserErrors( ctxt, staticCFunction(::err) as xmlSchemaValidityErrorFunc?, staticCFunction(::warn) as xmlSchemaValidityWarningFunc?, stderr )
val schema = xmlSchemaParse(ctxt) xmlSchemaFreeParserCtxt(ctxt)
val doc = xmlReadFile(xmlFileName, null, 0) if (doc == null) { println("Could not parse $xmlFileName") } else { val ctxt2 = xmlSchemaNewValidCtxt(schema)
xmlSchemaSetValidErrors( ctxt2, staticCFunction(::err) as xmlSchemaValidityErrorFunc?, staticCFunction(::warn) as xmlSchemaValidityWarningFunc?, stderr )
val ret = xmlSchemaValidateDoc(ctxt2, doc) if (ret == 0) println("$xmlFileName validates") else if (ret > 0) println("$xmlFileName fails to validate") else println("$xmlFileName generated an internal error") xmlSchemaFreeValidCtxt(ctxt2) xmlFreeDoc(doc) }
if (schema != null) xmlSchemaFree(schema) xmlSchemaCleanupTypes() xmlCleanupParser() xmlMemoryDump()
}</lang> Finally, the resulting .kexe file should be executed passing it similar command line arguments to the C entry to produce the following output.
$ ./xmlval.kexe shiporder.xml shiporder.xsd shiporder.xml validates
Nim
As in the C version, we use “libxml2” for the validation. As there is no Nim binding for this library, we provide the necessary definitions in our program (three types and six procedures). There is nothing more to do. In Nim, interfacing with C is often very easy.
Our program is based on the C version with many differences. In particular, we use the function “xmlSchemaValidateFile” rather than the function “xmlSchemaValidateDoc”.
<lang Nim>import os, strformat
const LibXml = "libxml2.so"
type
XmlSchemaParserCtxtPtr = pointer XmlSchemaPtr = pointer XmlSchemaValidCtxtPtr = pointer
- Declaration of needed "libxml2" procedures.
proc xmlSchemaNewParserCtxt(url: cstring): XmlSchemaParserCtxtPtr
{.cdecl, dynlib: LibXml, importc: "xmlSchemaNewParserCtxt".}
proc xmlSchemaParse(ctxt: XmlSchemaParserCtxtPtr): XmlSchemaPtr
{.cdecl, dynlib: LibXml, importc: "xmlSchemaParse".}
proc xmlSchemaFreeParserCtxt(ctxt: XmlSchemaParserCtxtPtr)
{.cdecl, dynlib: LibXml, importc: "xmlSchemaFreeParserCtxt".}
proc xmlSchemaNewValidCtxt(schema: XmlSchemaPtr): XmlSchemaValidCtxtPtr
{.cdecl, dynlib: LibXml, importc: "xmlSchemaNewValidCtxt".}
proc xmlSchemaValidateFile(ctxt: XmlSchemaValidCtxtPtr; filename: cstring; options: cint): cint
{.cdecl, dynlib: LibXml, importc: "xmlSchemaValidateFile".}
proc xmlSchemaFreeValidCtxt(ctxt: XmlSchemaValidCtxtPtr)
{.cdecl, dynlib: LibXml, importc: "xmlSchemaFreeValidCtxt".}
if paramCount() != 2:
quit &"Usage: {getAppFilename().lastPathPart} <XML Document Name> <XSD Document Name", QuitFailure
let xmlFilename = paramStr(1) let xsdFilename = paramStr(2)
- Parse XML schema file.
let parserCtxt = xmlSchemaNewParserCtxt(xsdFilename) let schema = parserCtxt.xmlSchemaParse() parserCtxt.xmlSchemaFreeParserCtxt()
- Validate XML file using XML schema.
let validCtxt = schema.xmlSchemaNewValidCtxt() case validCtxt.xmlSchemaValidateFile(xmlFilename, 0) of 0:
echo &"“{xmlFilename}” validates."
of -1:
echo &"“{xmlFilename}” validation generated an internal error."
else:
echo &"“{xmlFilename}” fails to validate."
validCtxt.xmlSchemaFreeValidCtxt()</lang>
- Output:
Using command ./xml_validate shiporder.xml shiporder.xsd
:
“shiporder.xml” validates.
Using a modified file “shiporder1.xml” where tag “orderperson” has been replaced by “orderperson1”:
Entity: line 6: Schemas validity error : Element 'orderperson1': This element is not expected. Expected is ( orderperson ). “shiporder1.xml” fails to validate.
Perl
<lang perl>#!/usr/bin/env perl -T use 5.018_002; use warnings; use Try::Tiny; use XML::LibXML;
our $VERSION = 1.000_000;
my $parser = XML::LibXML->new();
my $good_xml = '<a>5</a>'; my $bad_xml = '<a>5foobar</a>'; my $xmlschema_markup = <<'END'; <xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:element name="a" type="xsd:integer"/>
</xsd:schema> END
my $xmlschema = XML::LibXML::Schema->new( string => $xmlschema_markup );
for ( $good_xml, $bad_xml ) {
my $doc = $parser->parse_string($_); try { $xmlschema->validate($doc); } finally { if (@_) { say "Not valid: @_"; } else { say 'Valid'; } };
}</lang>
- Output:
Valid Not valid: unknown-7fe99976a9a0:0: Schemas validity error : Element 'a': Element content is not allowed, because the type definition is simple.
Phix
Note that error handling has been delegated to within libxml.e, specifically xmlSchemaNewParserCtxt() and xmlSchemaNewValidCtxt() assign an internal handler, which resorts to xmlGetLastError() and therefore needs to use a bit of cffi, that is rather than using the (odd-looking) error it is actually passed. The libxml.e wrapper was penned specifically for this task and is just about as bare-bones as it could ever possibly be, and win32-only, for now.
-- -- demo\rosetta\Validate_XML.exw -- ============================= -- without js requires(32) -- let me know if you can get this to work on 64bit requires(WINDOWS) -- "" if you can get this to work on linux constant dl = `Download rosetta\libxml\ from http://phix.x10.mx/pmwiki/pmwiki.php?n=Main.libxml` assert(get_file_type("libxml")=FILETYPE_DIRECTORY,dl) include libxml\libxml.e constant XSDFileName = `libxml\shiporder.xsd`, -- (versions 2 & 3 also included in "") XMLFileName = `libxml\shiporder.xml` xmlLineNumbersDefault(1) atom pctxt = xmlSchemaNewParserCtxt(XSDFileName), schema = xmlSchemaParse(pctxt) xmlSchemaFreeParserCtxt(pctxt) atom doc = xmlReadFile(XMLFileName, NULL, 0) if doc=NULL then printf(2, "Could not parse %s\n", {XMLFileName}) else atom vctxt = xmlSchemaNewValidCtxt(schema) integer ret = xmlSchemaValidateDoc(vctxt, doc) if ret=0 then printf(1,"%s validates\n", {XMLFileName}) elsif ret>0 then printf(1,"%s fails to validate\n", {XMLFileName}) else printf(1,"%s validation generated an internal error\n", {XMLFileName}) end if xmlSchemaFreeValidCtxt(vctxt) xmlFreeDoc(doc) end if if schema!=NULL then xmlSchemaFree(schema) end if xmlSchemaCleanupTypes() xmlCleanupParser() xmlMemoryDump()
- Output:
libxml\shiporder.xml validates
Performing the same error handling check as Nim, ie changing orderperson to orderperson1 (twice) results in:
Error/Warning in line 6 Element 'orderperson1': This element is not expected. Expected is ( orderperson ). libxml\shiporder.xml fails to validate
All three formats of the xsd file as given on the W3 page give identical results, for both with and without that error.
PHP
<lang php> libxml_use_internal_errors(true);
$xml = new DOMDocument(); $xml->load('shiporder.xml');
if (!$xml->schemaValidate('shiporder.xsd')) {
var_dump(libxml_get_errors()); exit;
} else {
echo 'success';
} </lang>
- Output:
using valid shiporder.xml and shiporder.xsd: success Done. using invalid shiporder.xml and valid shiporder.xsd: array(1) { [0] => class LibXMLError#2 (6) { public $level => int(2) public $code => int(1871) public $column => int(0) public $message => string(74) "Element 'foo': This element is not expected. Expected is ( orderperson ). " public $file => string(43) "file:/C:/xampp/htdocs/rosetta/shiporder.xml" public $line => int(4) } } Done.
Python
<lang python>#!/bin/python from __future__ import print_function import lxml from lxml import etree
if __name__=="__main__":
parser = etree.XMLParser(dtd_validation=True) schema_root = etree.XML(\ <xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"> <xsd:element name="a" type="xsd:integer"/> </xsd:schema> ) schema = etree.XMLSchema(schema_root)
#Good xml parser = etree.XMLParser(schema = schema) try: root = etree.fromstring("<a>5</a>", parser) print ("Finished validating good xml") except lxml.etree.XMLSyntaxError as err: print (err)
#Bad xml parser = etree.XMLParser(schema = schema) try: root = etree.fromstring("<a>5foobar</a>", parser) except lxml.etree.XMLSyntaxError as err: print (err)</lang>
- Output:
Finished validating good xml Element 'a': Element content is not allowed, because the type definition is simple.
Raku
(formerly Perl 6)
<lang perl6>
- Reference: https://github.com/libxml-raku/LibXML-raku
use v6.d; use LibXML; use LibXML::Schema;
my $good_xml = '<a>5</a>'; my $bad_xml = '<a>5foobar</a>';
my $xsdschema = q:to<EOF>;
<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"> <xsd:element name="a" type="xsd:integer"/> </xsd:schema>
EOF
my LibXML $p .= new();
for ( $good_xml, $bad_xml ) {
my $x = $p.parse: :string($_); try { LibXML::Schema.new( string => $xsdschema ).validate( $x ) } !$! ?? say "Valid." !! say $!.message() ;
}</lang>
- Output:
Valid. Schemas validity error : Element 'a': Element content is not allowed, because the type definition is simple.
Scala
<lang Scala>import java.net.URL
import javax.xml.XMLConstants.W3C_XML_SCHEMA_NS_URI import javax.xml.transform.stream.StreamSource import javax.xml.validation.SchemaFactory import javax.xml.ws.Holder import org.xml.sax.{ErrorHandler, SAXException, SAXParseException}
object XmlValidation extends App {
val (schemaLocation, documentLocation) = (new URL("http://venus.eas.asu.edu/WSRepository/xml/Courses.xsd") , new URL("http://venus.eas.asu.edu/WSRepository/xml/Courses.xml"))
println(s"Document is ${if (validate(schemaLocation, documentLocation)) "valid" else "invalid"}.")
// A more complete validator def validate(schemaLocation: URL, documentLocation: URL): Boolean = { val factory = SchemaFactory.newInstance(W3C_XML_SCHEMA_NS_URI) val valid = new Holder[Boolean](true) try { val validator = factory.newSchema(schemaLocation).newValidator // Get some better diagnostics out validator.setErrorHandler(new ErrorHandler() { override def warning(exception: SAXParseException) = println("warning: " + exception.getMessage)
override def error(exception: SAXParseException) = { println("error: " + exception.getMessage) valid.value = false }
override def fatalError(exception: SAXParseException) = { println("fatal error: " + exception.getMessage) throw exception } }) validator.validate(new StreamSource(documentLocation.toString)) valid.value } catch { case _: SAXException => // Already reported above false case e: Exception => // If this is the only thing that throws, it's a gross error println(e) false } }
}</lang>
Sidef
<lang ruby>require('XML::LibXML')
func is_valid_xml(str, schema) {
var parser = %O<XML::LibXML>.new var xmlschema = %O<XML::LibXML::Schema>.new(string => schema)
try { xmlschema.validate(parser.parse_string(str)) true } catch { false }
}
var good_xml = '<a>5</a>' var bad_xml = '<a>5foobar</a>'
var xmlschema_markup = <<'END' <xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<xsd:element name="a" type="xsd:integer"/>
</xsd:schema> END
[good_xml, bad_xml].each { |xml|
say "is_valid_xml(#{xml.dump}) : #{is_valid_xml(xml, xmlschema_markup)}"
}</lang>
- Output:
is_valid_xml("<a>5</a>") : true is_valid_xml("<a>5<b>foobar</b></a>") : false
Visual Basic .NET
Compiler: Roslyn Visual Basic (language version >= 14, e.g. with Visual Studio 2015)
<lang vbnet>Option Compare Binary Option Explicit On Option Infer On Option Strict On
Imports System.Xml Imports System.Xml.Schema
Module Program
Function GetValidationErrors(doc As XDocument, schemaSet As XmlSchemaSet) As IList(Of ValidationEventArgs) GetValidationErrors = New List(Of ValidationEventArgs) doc.Validate(schemaSet, Sub(sender, e) GetValidationErrors.Add(e)) End Function
Sub Main() ' These functions are declared in another module found below. Dim schema = GetSchema() Dim document = GetDocument()
Dim schemaSet As New XmlSchemaSet() schemaSet.Add(XmlSchema.Read(schema.CreateReader(), Nothing))
Dim errors = GetValidationErrors(document, schemaSet) For Each e In errors Console.WriteLine($"Validation {e.Severity}:{vbCrLf}{e.Message}") Next
If errors.Count = 0 Then Console.WriteLine("The document is valid.") End Sub
End Module</lang>
- Output:
Validation Error: The 'an-attribute' attribute is invalid - The value 'wrong' is invalid according to its datatype 'http://www.w3.org/2001/XMLSchema:boolean' - The string 'wrong' is not a valid Boolean value.
An alternative is to use XmlReader (like the C# and F# examples [as of 2019-08-06]).
<lang vbnet> Function GetValidationErrorsXmlReader(doc As XDocument, schemaSet As XmlSchemaSet, warnings As Boolean) As IList(Of ValidationEventArgs)
GetValidationErrorsReader = New List(Of ValidationEventArgs)
Dim settings As New XmlReaderSettings() With settings .ValidationType = ValidationType.Schema .Schemas = schemaSet If warnings Then .ValidationFlags = .ValidationFlags Or XmlSchemaValidationFlags.ReportValidationWarnings End With
AddHandler settings.ValidationEventHandler, Sub(sender, e) GetValidationErrorsReader.Add(e)
Using reader = XmlReader.Create(doc.CreateReader(), settings) Do While reader.Read() : Loop End Using End Function</lang>
Creating the documents (same as F#) from strings (does not handle syntax errors):
<lang vbnet>Module Constants
Const SCHEMA As String =
"<?xml version='1.0'?> <xs:schema id='an-element' targetNamespace='example' xmlns:mstns='example' xmlns='example' xmlns:xs='http://www.w3.org/2001/XMLSchema' attributeFormDefault='unqualified' elementFormDefault='qualified'>
<xs:element name='an-element'> <xs:complexType> <xs:sequence minOccurs='0' maxOccurs='unbounded'> <xs:element name='another-element' nillable='true'> <xs:complexType> <xs:simpleContent> <xs:extension base='xs:string'> <xs:attribute name='an-attribute' form='unqualified' type='xs:boolean'/> </xs:extension> </xs:simpleContent> </xs:complexType> </xs:element> </xs:sequence> </xs:complexType> </xs:element>
</xs:schema>"
Const DOCUMENT As String =
"<?xml version='1.0'?> <an-element xmlns='example'>
<another-element an-attribute='false'>...</another-element> <another-element an-attribute='wrong'>123</another-element>
</an-element>"
Function GetSchema() As XDocument Return XDocument.Parse(SCHEMA) End Function
Function GetDocument() As XDocument Return XDocument.Parse(DOCUMENT) End Function
End Module</lang>
Alternatively, we can be cheeky and use VB's XML literals...
<lang vbnet>Module Constants
Function GetDocument() As XDocument Return _ <?xml version="1.0"?> <an-element xmlns="example"> <another-element an-attribute="false">...</another-element> <another-element an-attribute="wrong"> 123</another-element> </an-element> End Function
Function GetSchema() As XDocument Return _ <?xml version="1.0"?> <xs:schema id="an-element" targetNamespace="example" xmlns:mstns="example" xmlns="example" xmlns:xs="http://www.w3.org/2001/XMLSchema" attributeFormDefault="unqualified" elementFormDefault="qualified"> <xs:element name="an-element"> <xs:complexType> <xs:sequence minOccurs="0" maxOccurs="unbounded"> <xs:element name="another-element" nillable="true"> <xs:complexType> <xs:simpleContent> <xs:extension base="xs:string"> <xs:attribute name="an-attribute" form="unqualified" type="xs:boolean"/> </xs:extension> </xs:simpleContent> </xs:complexType> </xs:element> </xs:sequence> </xs:complexType> </xs:element> </xs:schema> End Function
End Module</lang>
Wren
Wren has no XML support whatever, either built-in or (AFAIK) via third parties. We therefore use an embedded program so we can ask the C host to communicate with Libxml2 for us. <lang ecmascript>/* xml_validation.wren */
class Args {
foreign static xmlFilename
foreign static xsdFilename
}
foreign class XmlSchemaPtr {
construct new() {}
}
foreign class XmlSchemaParserCtxtPtr {
construct new(url) {}
foreign parse(schema)
foreign freeParserCtxt()
}
foreign class XmlSchemaValidCtxtPtr {
construct new(schema) {}
foreign validateFile(filename, options)
foreign freeValidCtxt()
}
var xmlFilename = Args.xmlFilename var xsdFilename = Args.xsdFilename
// parse xml schema file var parserCtxt = XmlSchemaParserCtxtPtr.new(xsdFilename) var schema = XmlSchemaPtr.new() parserCtxt.parse(schema) parserCtxt.freeParserCtxt()
// validate xml file using schema var validCtxt = XmlSchemaValidCtxtPtr.new(schema) var res = validCtxt.validateFile(xmlFilename, 0) if (res == 0) {
System.print("'%(xmlFilename)' validates.")
} else if (res == -1) {
System.print("'%(xmlFilename)' validation generated an internal error.")
} else {
System.print("'%(xmlFilename)' fails to validate.")
}
validCtxt.freeValidCtxt()</lang>
We now embed this in the following C program, compile and run it.
<lang c>/* built with: gcc xml_validation.c -o xml_validation -I/usr/include/libxml2 -lxml2 -lwren -lm */
- include <stdio.h>
- include <stdlib.h>
- include <string.h>
- include <libxml2/libxml/xmlschemastypes.h>
- include "wren.h"
/* C <=> Wren interface functions */
char *xmlFilename, *xsdFilename;
void C_xmlFilename(WrenVM* vm) {
wrenSetSlotString(vm, 0, xmlFilename);
}
void C_xsdFilename(WrenVM* vm) {
wrenSetSlotString(vm, 0, xsdFilename);
}
void C_xmlSchemaPtrAllocate(WrenVM* vm) {
wrenSetSlotNewForeign(vm, 0, 0, sizeof(xmlSchemaPtr));
}
void C_xmlSchemaParserCtxtPtrAllocate(WrenVM* vm) {
xmlSchemaParserCtxtPtr* pctxt = (xmlSchemaParserCtxtPtr*)wrenSetSlotNewForeign(vm, 0, 0, sizeof(xmlSchemaParserCtxtPtr)); const char *url = wrenGetSlotString(vm, 1); *pctxt = xmlSchemaNewParserCtxt(url);
}
void C_xmlSchemaValidCtxtPtrAllocate(WrenVM* vm) {
xmlSchemaValidCtxtPtr* pctxt = (xmlSchemaValidCtxtPtr*)wrenSetSlotNewForeign(vm, 0, 0, sizeof(xmlSchemaValidCtxtPtr)); xmlSchemaPtr schema = *(xmlSchemaPtr*)wrenGetSlotForeign(vm, 1); *pctxt = xmlSchemaNewValidCtxt(schema);
}
void C_parse(WrenVM* vm) {
xmlSchemaParserCtxtPtr ctxt = *(xmlSchemaParserCtxtPtr*)wrenGetSlotForeign(vm, 0); xmlSchemaPtr* pschema = (xmlSchemaPtr*)wrenGetSlotForeign(vm, 1); *pschema = xmlSchemaParse(ctxt);
}
void C_freeParserCtxt(WrenVM* vm) {
xmlSchemaParserCtxtPtr ctxt = *(xmlSchemaParserCtxtPtr*)wrenGetSlotForeign(vm, 0); xmlSchemaFreeParserCtxt(ctxt);
}
void C_validateFile(WrenVM* vm) {
xmlSchemaValidCtxtPtr ctxt = *(xmlSchemaValidCtxtPtr*)wrenGetSlotForeign(vm, 0); const char *filename = wrenGetSlotString(vm, 1); int options = (int)wrenGetSlotDouble(vm, 2); int res = xmlSchemaValidateFile(ctxt, filename, options); wrenSetSlotDouble(vm, 0, (double)res);
}
void C_freeValidCtxt(WrenVM* vm) {
xmlSchemaValidCtxtPtr ctxt = *(xmlSchemaValidCtxtPtr*)wrenGetSlotForeign(vm, 0); xmlSchemaFreeValidCtxt(ctxt);
}
WrenForeignClassMethods bindForeignClass(WrenVM* vm, const char* module, const char* className) {
WrenForeignClassMethods methods; methods.allocate = NULL; methods.finalize = NULL; if (strcmp(module, "main") == 0) { if (strcmp(className, "XmlSchemaPtr") == 0) { methods.allocate = C_xmlSchemaPtrAllocate; } else if (strcmp(className, "XmlSchemaParserCtxtPtr") == 0) { methods.allocate = C_xmlSchemaParserCtxtPtrAllocate; } else if (strcmp(className, "XmlSchemaValidCtxtPtr") == 0) { methods.allocate = C_xmlSchemaValidCtxtPtrAllocate; } } return methods;
}
WrenForeignMethodFn bindForeignMethod(
WrenVM* vm, const char* module, const char* className, bool isStatic, const char* signature) { if (strcmp(module, "main") == 0) { if (strcmp(className, "Args") == 0) { if (isStatic && strcmp(signature, "xmlFilename") == 0) return C_xmlFilename; if (isStatic && strcmp(signature, "xsdFilename") == 0) return C_xsdFilename; } else if (strcmp(className, "XmlSchemaParserCtxtPtr") == 0) { if (!isStatic && strcmp(signature, "parse(_)") == 0) return C_parse; if (!isStatic && strcmp(signature, "freeParserCtxt()") == 0) return C_freeParserCtxt; } else if (strcmp(className, "XmlSchemaValidCtxtPtr") == 0) { if (!isStatic && strcmp(signature, "validateFile(_,_)") == 0) return C_validateFile; if (!isStatic && strcmp(signature, "freeValidCtxt()") == 0) return C_freeValidCtxt; } } return NULL;
}
static void writeFn(WrenVM* vm, const char* text) {
printf("%s", text);
}
void errorFn(WrenVM* vm, WrenErrorType errorType, const char* module, const int line, const char* msg) {
switch (errorType) { case WREN_ERROR_COMPILE: printf("[%s line %d] [Error] %s\n", module, line, msg); break; case WREN_ERROR_STACK_TRACE: printf("[%s line %d] in %s\n", module, line, msg); break; case WREN_ERROR_RUNTIME: printf("[Runtime Error] %s\n", msg); break; }
}
char *readFile(const char *fileName) {
FILE *f = fopen(fileName, "r"); fseek(f, 0, SEEK_END); long fsize = ftell(f); rewind(f); char *script = malloc(fsize + 1); fread(script, 1, fsize, f); fclose(f); script[fsize] = 0; return script;
}
int main(int argc, char **argv) {
if (argc <= 2) {
printf("Usage: %s <XML Document Name> <XSD Document Name>\n", argv[0]); return 0; }
xmlFilename = argv[1]; xsdFilename = argv[2]; WrenConfiguration config; wrenInitConfiguration(&config); config.writeFn = &writeFn; config.errorFn = &errorFn; config.bindForeignClassFn = &bindForeignClass; config.bindForeignMethodFn = &bindForeignMethod; WrenVM* vm = wrenNewVM(&config); const char* module = "main"; const char* fileName = "xml_validation.wren"; char *script = readFile(fileName); WrenInterpretResult result = wrenInterpret(vm, module, script); switch (result) { case WREN_RESULT_COMPILE_ERROR: printf("Compile Error!\n"); break; case WREN_RESULT_RUNTIME_ERROR: printf("Runtime Error!\n"); break; case WREN_RESULT_SUCCESS: break; } wrenFreeVM(vm); free(script); return 0;
}</lang>
- Output:
Using command ./xml_validation shiporder.xml shiporder.xsd
:
'shiporder.xml' validates.
Using a modified file “shiporder1.xml” where tag “orderperson” has been replaced by “orderperson1”:
Entity: line 6: Schemas validity error : Element 'orderperson1': This element is not expected. Expected is ( orderperson ). 'shiporder1.xml' fails to validate.