Merge pull request lestrrat-go#69 from lestrrat-go/topic/with-uri

allow ways to specify path/uri when parsing XSD
icysoft · Nov 23, 2020 · e6d9de6 · e6d9de6
2 parents a52d2c7 + 4681c5b
commit e6d9de6
Show file tree

Hide file tree

Showing 15 changed files with 817 additions and 8 deletions.
diff --git a/clib/clib.go b/clib/clib.go
@@ -36,6 +36,7 @@ package clib
 #include <libxml/xpathInternals.h>
 #include <libxml/c14n.h>
 #include <libxml/xmlschemas.h>
+#include <libxml/schemasInternals.h>
 
 static inline void MY_nilErrorHandler(void *ctx, const char *msg, ...) {}
 
@@ -343,6 +344,7 @@ import (
 	"unsafe"
 
 	"github.com/lestrrat-go/libxml2/internal/debug"
+	"github.com/lestrrat-go/libxml2/internal/option"
 	"github.com/pkg/errors"
 )
 
@@ -465,7 +467,14 @@ func ReportErrors(b bool) {
 }
 
 func xmlCtxtLastError(ctx PtrSource) error {
-	e := C.MY_xmlCtxtLastError(unsafe.Pointer(ctx.Pointer()))
+	return xmlCtxtLastErrorRaw(ctx.Pointer())
+}
+
+func xmlCtxtLastErrorRaw(ctx uintptr) error {
+	e := C.MY_xmlCtxtLastError(unsafe.Pointer(ctx))
+	if e == nil {
+		return errors.New(`unknown error`)
+	}
 	msg := strings.TrimSuffix(C.GoString(e.message), "\n")
 	return errors.Errorf("Entity: line %v: parser error : %v", e.line, msg)
 }
@@ -2116,11 +2125,41 @@ func XMLTextData(n PtrSource) string {
 	return xmlCharToString(nptr.content)
 }
 
-func XMLSchemaParse(buf []byte) (uintptr, error) {
-	parserCtx := C.xmlSchemaNewMemParserCtxt(
-		(*C.char)(unsafe.Pointer(&buf[0])),
-		C.int(len(buf)),
-	)
+func XMLSchemaParse(buf []byte, options ...option.Interface) (uintptr, error) {
+	var uri string
+	var encoding string
+	var coptions int
+	for _, opt := range options {
+		switch opt.Name() {
+		case option.OptKeyWithURI:
+			uri = opt.Value().(string)
+		}
+	}
+
+	docctx := C.xmlCreateMemoryParserCtxt((*C.char)(unsafe.Pointer(&buf[0])), C.int(len(buf)))
+	if docctx == nil {
+		return 0, errors.New("error creating doc parser")
+	}
+
+	var curi *C.char
+	if uri != "" {
+		curi = C.CString(uri)
+		defer C.free(unsafe.Pointer(curi))
+	}
+
+	var cencoding *C.char
+	if encoding != "" {
+		cencoding = C.CString(encoding)
+		defer C.free(unsafe.Pointer(cencoding))
+	}
+
+	doc := C.xmlCtxtReadMemory(docctx, (*C.char)(unsafe.Pointer(&buf[0])), C.int(len(buf)), curi, cencoding, C.int(coptions))
+	if doc == nil {
+		return 0, errors.Errorf("failed to read schema from memory: %v",
+			xmlCtxtLastErrorRaw(uintptr(unsafe.Pointer(docctx))))
+	}
+
+	parserCtx := C.xmlSchemaNewDocParserCtxt((*C.xmlDoc)(unsafe.Pointer(doc)))
 	if parserCtx == nil {
 		return 0, errors.New("failed to create parser")
 	}

diff --git a/internal/option/interface.go b/internal/option/interface.go
@@ -0,0 +1,5 @@
+package option
+
+const (
+	OptKeyWithURI = `with-uri`
+)
diff --git a/internal/option/option.go b/internal/option/option.go
@@ -0,0 +1,25 @@
+package option
+
+type Interface interface {
+	Name() string
+	Value() interface{}
+}
+
+type Option struct {
+	name  string
+	value interface{}
+}
+
+func New(name string, value interface{}) *Option {
+	return &Option{
+		name:  name,
+		value: value,
+	}
+}
+
+func (o *Option) Name() string {
+	return o.name
+}
+func (o *Option) Value() interface{} {
+	return o.value
+}
diff --git a/test/go_libxml2_local.xml b/test/go_libxml2_local.xml
@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<libxml2 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xmlns="http://xmlsoft.org/"
+         xsi:schemaLocation="http://xmlsoft.org/ ./schema/projects/go_libxml2_local.xsd">
+
+  <sub attrReq="foo" attrOpt="bar">
+    <nestedInclude hashType="sha1">4cfcf843c66979eb1df2bd0c52817edb753a52ba</nestedInclude>
+  </sub>
+  <sub attrReq="foo2">
+    <sub2>this is a test string only.</sub2>
+    <nestedInclude hashType="sha512">be218408a748759fb98363593b8f544eb054171bced856ca98bd972823dec0b07b205453fc3c46f23c934d0959f1e05b609c011b6ada84a7050ad7c910b24bf1</nestedInclude>
+  </sub>
+  <sub attrReq="foo3" attrBoolNoDef="false">
+    <sub2>foobar</sub2>
+    <nestedInclude hashType="md5">f7b34871a562283ee92bbda00485eb45</nestedInclude>
+  </sub>
+
+</libxml2>
diff --git a/test/go_libxml2_remote.xml b/test/go_libxml2_remote.xml
@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<libxml2 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xmlns="http://xmlsoft.org/"
+         xsi:schemaLocation="http://xmlsoft.org/ http://schema.xml.r00t2.io/projects/go_libxml2.xsd">
+
+  <sub attrReq="foo" attrOpt="bar">
+    <nestedInclude hashType="sha1">4cfcf843c66979eb1df2bd0c52817edb753a52ba</nestedInclude>
+  </sub>
+  <sub attrReq="foo2">
+    <sub2>this is a test string only.</sub2>
+    <nestedInclude hashType="sha512">be218408a748759fb98363593b8f544eb054171bced856ca98bd972823dec0b07b205453fc3c46f23c934d0959f1e05b609c011b6ada84a7050ad7c910b24bf1</nestedInclude>
+  </sub>
+  <sub attrReq="foo3" attrBoolNoDef="false">
+    <sub2>foobar</sub2>
+    <nestedInclude hashType="md5">f7b34871a562283ee92bbda00485eb45</nestedInclude>
+  </sub>
+
+</libxml2>
diff --git a/test/schema/lib/types/cksum.xsd b/test/schema/lib/types/cksum.xsd
@@ -0,0 +1,76 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema"
+           elementFormDefault="qualified"
+           attributeFormDefault="unqualified">
+
+    <xs:include schemaLocation="./std.xsd"/>
+    <xs:include schemaLocation="./net.xsd"/>
+    <xs:include schemaLocation="./unix.xsd"/>
+
+    <xs:simpleType name="t_cksum_algo">
+        <!-- Geared towards python. -->
+        <!-- tuple(sorted(list(hashlib.algorithms_available.union(set(('adler32', 'crc32')))))) -->
+        <xs:restriction base="xs:string">
+            <xs:enumeration value="adler32"/>
+            <xs:enumeration value="blake2b"/>
+            <xs:enumeration value="blake2s"/>
+            <xs:enumeration value="crc32"/>
+            <xs:enumeration value="md4"/>
+            <xs:enumeration value="md5"/>
+            <xs:enumeration value="md5-sha1"/>
+            <xs:enumeration value="mdc2"/>
+            <xs:enumeration value="ripemd160"/>
+            <xs:enumeration value="sha1"/>
+            <xs:enumeration value="sha224"/>
+            <xs:enumeration value="sha256"/>
+            <xs:enumeration value="sha384"/>
+            <xs:enumeration value="sha3_224"/>
+            <xs:enumeration value="sha3_256"/>
+            <xs:enumeration value="sha3_384"/>
+            <xs:enumeration value="sha3_512"/>
+            <xs:enumeration value="sha512"/>
+            <xs:enumeration value="sha512_224"/>
+            <xs:enumeration value="sha512_256"/>
+            <xs:enumeration value="shake_128"/>
+            <xs:enumeration value="shake_256"/>
+            <xs:enumeration value="sm3"/>
+            <xs:enumeration value="whirlpool"/>
+            <xs:whiteSpace value="collapse"/>
+        </xs:restriction>
+    </xs:simpleType>
+
+    <xs:complexType name="t_cksum_file">
+        <xs:simpleContent>
+            <xs:extension base="t_net_generic_resource">
+                <xs:attribute name="hashType" use="required" type="t_cksum_algo"/>
+                <xs:attribute name="fileType" use="required" type="t_cksum_file_filetype"/>
+                <xs:attribute name="filePath" use="optional" type="t_unix_filepath"/>
+            </xs:extension>
+        </xs:simpleContent>
+    </xs:complexType>
+
+    <xs:simpleType name="t_cksum_file_filetype">
+        <xs:restriction base="xs:string">
+            <xs:enumeration value="gnu"/>
+            <xs:enumeration value="bsd"/>
+            <xs:whiteSpace value="collapse"/>
+        </xs:restriction>
+    </xs:simpleType>
+
+    <xs:complexType name="t_cksum_hash">
+        <xs:simpleContent>
+            <xs:extension base="t_std_nonempty">
+                <xs:attribute name="hashType" use="required" type="t_cksum_algo"/>
+            </xs:extension>
+        </xs:simpleContent>
+    </xs:complexType>
+
+    <xs:complexType name="t_cksum_verify">
+        <xs:choice minOccurs="1" maxOccurs="unbounded">
+            <xs:element name="checksum" minOccurs="0" maxOccurs="unbounded" type="t_cksum_hash">
+            </xs:element>
+            <xs:element name="checksumFile" minOccurs="0" maxOccurs="unbounded" type="t_cksum_file"/>
+        </xs:choice>
+    </xs:complexType>
+
+</xs:schema>