diff options
| -rwxr-xr-x | doc/lib.txt | 13 | ||||
| -rw-r--r-- | lib/pure/xmldom.nim | 1009 | ||||
| -rw-r--r-- | lib/pure/xmldomparser.nim | 110 | ||||
| -rwxr-xr-x | web/news.txt | 2 | ||||
| -rwxr-xr-x | web/nimrod.ini | 4 |
5 files changed, 1136 insertions, 2 deletions
diff --git a/doc/lib.txt b/doc/lib.txt index 7167cbf4e..06edf997c 100755 --- a/doc/lib.txt +++ b/doc/lib.txt @@ -68,6 +68,9 @@ String handling is done in O(1) instead of O(n). * `unidecode <unidecode.html>`_ + This module provides Unicode to ASCII transliterations: + It finds the sequence of ASCII characters that is the closest approximation + to the Unicode string. Generic Operating System Services @@ -162,6 +165,16 @@ Parsers scheme for lexers and parsers. This is used by the diverse parsing modules. +XML Processing +-------------- + +* `xmldom <xmldom.html>`_ + This module implements the XML DOM Level 2. + +* `xmldomparser <xmldomparser.html>`_ + This module parses a XML Document into a XML DOM Document representation. + + Code generation --------------- diff --git a/lib/pure/xmldom.nim b/lib/pure/xmldom.nim new file mode 100644 index 000000000..12578a793 --- /dev/null +++ b/lib/pure/xmldom.nim @@ -0,0 +1,1009 @@ +# +# +# Nimrod's Runtime Library +# (c) Copyright 2010 Dominik Picheta +# +# See the file "copying.txt", included in this +# distribution, for details about the copyright. +# + + +import strutils +## This module implements the XML DOM Level 2 + +#http://www.w3.org/TR/2000/REC-DOM-Level-2-Core-20001113/core.html +#DOMString = String +#DOMTimeStamp = int16 ?? + +#DECLARATIONS + +#Exceptions +type + EDOMException* = object of E_Base #Base exception object for all DOM Exceptions + EDOMStringSizeErr* = object of EDOMException #If the specified range of text does not fit into a DOMString + #Currently not used(Since DOMString is just string) + EHierarchyRequestErr* = object of EDOMException #If any node is inserted somewhere it doesn't belong + EIndexSizeErr* = object of EDOMException #If index or size is negative, or greater than the allowed value + EInuseAttributeErr* = object of EDOMException #If an attempt is made to add an attribute that is already in use elsewhere + EInvalidAccessErr* = object of EDOMException #If a parameter or an operation is not supported by the underlying object. + EInvalidCharacterErr* = object of EDOMException #This exception is raised when a string parameter contains an illegal character + EInvalidModificationErr* = object of EDOMException #If an attempt is made to modify the type of the underlying object. + EInvalidStateErr* = object of EDOMException #If an attempt is made to use an object that is not, or is no longer, usable. + ENamespaceErr* = object of EDOMException #If an attempt is made to create or change an object in a way which is incorrect with regard to namespaces. + ENotFoundErr* = object of EDOMException #If an attempt is made to reference a node in a context where it does not exist + ENotSupportedErr* = object of EDOMException #If the implementation does not support the requested type of object or operation. + ENoDataAllowedErr* = object of EDOMException #If data is specified for a node which does not support data + ENoModificationAllowedErr* = object of EDOMException #If an attempt is made to modify an object where modifications are not allowed + ESyntaxErr* = object of EDOMException #If an invalid or illegal string is specified. + EWrongDocumentErr* = object of EDOMException #If a node is used in a different document than the one that created it (that doesn't support it) + +template newException(exceptn, message: expr): expr = + block: # open a new scope + var + e: ref exceptn + new(e) + e.msg = message + e + +const + ElementNode* = 1 + AttributeNode* = 2 + TextNode* = 3 + CDataSectionNode* = 4 + ProcessingInstructionNode* = 7 + CommentNode* = 8 + DocumentNode* = 9 + DocumentFragmentNode* = 11 + + # Nodes which are childless - Not sure about AttributeNode + childlessObjects = {DocumentNode, AttributeNode, TextNode, CDataSectionNode, ProcessingInstructionNode, CommentNode} + # Illegal characters + illegalChars = {'>', '<', '&', '"'} + + +type + Feature = tuple[name: string, version: string] + PDOMImplementation* = ref DOMImplementation + DOMImplementation = object + Features: seq[Feature] #Read-Only + + PNode* = ref Node + Node = object + attributes: seq[PAttr] #Read-only + childNodes*: seq[PNode] #Read-only + FLocalName: string #Read-only + FNamespaceURI: string #Read-only + FNodeName: string #Read-only + nodeValue*: string + FNodeType: int #Read-only + FOwnerDocument: PDocument #Read-Only + FParentNode: PNode #Read-Only + prefix*: string # Setting this should change some values... TODO! + + PElement* = ref Element + Element = object of Node + FTagName: string #Read-only + + PCharacterData = ref CharacterData + CharacterData = object of Node + data*: string + + PDocument* = ref Document + Document = object of Node + FImplementation: PDOMImplementation #Read-only + FDocumentElement: PElement #Read-only + + PAttr* = ref Attr + Attr = object of Node + FName: string #Read-only + FSpecified: bool #Read-only + value*: string + FOwnerElement: PElement #Read-only + + PDocumentFragment* = ref DocumentFragment + DocumentFragment = object of Node + + PText* = ref Text + Text = object of CharacterData + + PComment* = ref comment + Comment = object of CharacterData + + PCDataSection* = ref CDataSection + CDataSection = object of Text + + PProcessingInstruction* = ref ProcessingInstruction + ProcessingInstruction = object of Node + data*: string + FTarget: string #Read-only + +#DOMImplementation +proc getDOM*(): PDOMImplementation = + ##Returns a DOMImplementation + var DOMImpl: PDOMImplementation + new(DOMImpl) + DOMImpl.Features = @[(name: "core", version: "2.0"), (name: "core", version: "1.0"), (name: "XML", version: "2.0")] + return DOMImpl + +proc createDocument*(dom: PDOMImplementation, namespaceURI: string, qualifiedName: string): PDocument = + ##Creates an XML Document object of the specified type with its document element. + var doc: PDocument + new(doc) + doc.FNamespaceURI = namespaceURI + doc.FImplementation = dom + + var elTag: PElement + new(elTag) + elTag.FTagName = qualifiedName + elTag.FNodeName = qualifiedName + doc.FDocumentElement = elTag + doc.FNodeType = DocumentNode + + return doc + +proc createDocument*(dom: PDOMImplementation, n: PElement): PDocument = + ##Creates an XML Document object of the specified type with its document element. + #This procedure is not in the specification, it's provided for the parser. + var doc: PDocument + new(doc) + doc.FDocumentElement = n + doc.FImplementation = dom + doc.FNodeType = DocumentNode + + return doc + +proc hasFeature*(dom: PDOMImplementation, feature: string, version: string = ""): bool = + ##Returns ``true`` if this ``version`` of the DomImplementation implements ``feature``, otherwise ``false`` + for iName, iVersion in items(dom.Features): + if iName == feature: + if version == "": + return True + else: + if iVersion == version: + return True + return False + + +#Document +#Attributes + +proc implementation*(doc: PDocument): PDOMImplementation = + return doc.FImplementation + +proc documentElement*(doc: PDocument): PElement = + return doc.FDocumentElement + +#Internal procedures +proc findNodes(nl: PNode, name: string): seq[PNode] = + #Made for getElementsByTagName + var r: seq[PNode] = @[] + if nl.childNodes == nil: return @[] + if nl.childNodes.len() == 0: return @[] + + for i in items(nl.childNodes): + if i.FNodeType == ElementNode: + if i.FNodeName == name or name == "*": + r.add(i) + + if i.childNodes != nil: + if i.childNodes.len() != 0: + r.add(findNodes(i, name)) + + return r + +proc findNodesNS(nl: PNode, namespaceURI: string, localName: string): seq[PNode] = + #Made for getElementsByTagNameNS + var r: seq[PNode] = @[] + if nl.childNodes == nil: return @[] + if nl.childNodes.len() == 0: return @[] + + for i in items(nl.childNodes): + if i.FNodeType == ElementNode: + if (i.FNamespaceURI == namespaceURI or namespaceURI == "*") and (i.FLocalName == localName or localName == "*"): + r.add(i) + + if i.childNodes != nil: + if i.childNodes.len() != 0: + r.add(findNodesNS(i, namespaceURI, localName)) + + return r + + +#Procedures +proc createAttribute*(doc: PDocument, name: string): PAttr = + ##Creates an Attr of the given name. Note that the Attr instance can then be set on an Element using the setAttributeNode method. + ##To create an attribute with a qualified name and namespace URI, use the createAttributeNS method. + + #Check if name contains illegal characters + if illegalChars in name: + raise newException(EInvalidCharacterErr, "Invalid character") + + var AttrNode: PAttr + new(AttrNode) + AttrNode.FName = name + AttrNode.FNodeName = name + AttrNode.FLocalName = nil + AttrNode.prefix = nil + AttrNode.FNamespaceURI = nil + AttrNode.value = "" + AttrNode.FSpecified = False + return AttrNode + +proc createAttributeNS*(doc: PDocument, namespaceURI: string, qualifiedName: string): PAttr = + ##Creates an attribute of the given qualified name and namespace URI + + #Check if name contains illegal characters + if illegalChars in namespaceURI or illegalChars in qualifiedName: + raise newException(EInvalidCharacterErr, "Invalid character") + #Exceptions + if qualifiedName.contains(':'): + if namespaceURI == nil or namespaceURI == "": + raise newException(ENamespaceErr, "When qualifiedName contains a prefix namespaceURI cannot be nil") + elif qualifiedName.split(':')[0].toLower() == "xml" and namespaceURI != "http://www.w3.org/XML/1998/namespace": + raise newException(ENamespaceErr, + "When the namespace prefix is \"xml\" namespaceURI has to be \"http://www.w3.org/XML/1998/namespace\"") + elif qualifiedName.split(':')[1].toLower() == "xmlns" and namespaceURI != "http://www.w3.org/2000/xmlns/": + raise newException(ENamespaceErr, + "When the namespace prefix is \"xmlns\" namespaceURI has to be \"http://www.w3.org/2000/xmlns/\"") + + var AttrNode: PAttr + new(AttrNode) + AttrNode.FName = qualifiedName + AttrNode.FNodeName = qualifiedName + AttrNode.FSpecified = False + AttrNode.FNamespaceURI = namespaceURI + if qualifiedName.contains(':'): + AttrNode.prefix = qualifiedName.split(':')[0] + AttrNode.FLocalName = qualifiedName.split(':')[1] + else: + AttrNode.prefix = nil + AttrNode.FLocalName = qualifiedName + AttrNode.value = "" + + AttrNode.FNodeType = AttributeNode + return AttrNode + +proc createCDATASection*(doc: PDocument, data: string): PCDATASection = + ##Creates a CDATASection node whose value is the specified string. + var CData: PCDATASection + new(CData) + CData.data = data + CData.nodeValue = data + CData.FNodeName = "#text" #Not sure about this, but this is technically a TextNode + CData.FNodeType = CDataSectionNode + return CData + +proc createComment*(doc: PDocument, data: string): PComment = + ##Creates a Comment node given the specified string. + var Comm: PComment + new(Comm) + Comm.data = data + Comm.nodeValue = data + + Comm.FNodeType = CommentNode + return Comm + +proc createDocumentFragment*(doc: PDocument): PDocumentFragment = + ##Creates an empty DocumentFragment object. + var DF: PDocumentFragment + new(DF) + return DF + +proc createElement*(doc: PDocument, tagName: string): PElement = + ##Creates an element of the type specified. + + #Check if name contains illegal characters + if illegalChars in tagName: + raise newException(EInvalidCharacterErr, "Invalid character") + + var elNode: PElement + new(elNode) + elNode.FTagName = tagName + elNode.FNodeName = tagName + elNode.FLocalName = nil + elNode.prefix = nil + elNode.FNamespaceURI = nil + elNode.childNodes = @[] + elNode.attributes = @[] + + elNode.FNodeType = ElementNode + + return elNode + +proc createElementNS*(doc: PDocument, namespaceURI: string, qualifiedName: string): PElement = + ##Creates an element of the given qualified name and namespace URI. + if qualifiedName.contains(':'): + if namespaceURI == nil or namespaceURI == "": + raise newException(ENamespaceErr, "When qualifiedName contains a prefix namespaceURI cannot be nil") + elif qualifiedName.split(':')[0].toLower() == "xml" and namespaceURI != "http://www.w3.org/XML/1998/namespace": + raise newException(ENamespaceErr, + "When the namespace prefix is \"xml\" namespaceURI has to be \"http://www.w3.org/XML/1998/namespace\"") + + #Check if name contains illegal characters + if illegalChars in namespaceURI or illegalChars in qualifiedName: + raise newException(EInvalidCharacterErr, "Invalid character") + + var elNode: PElement + new(elNode) + elNode.FTagName = qualifiedName + elNode.FNodeName = qualifiedName + if qualifiedName.contains(':'): + elNode.prefix = qualifiedName.split(':')[0] + elNode.FLocalName = qualifiedName.split(':')[1] + else: + elNode.prefix = nil + elNode.FLocalName = qualifiedName + elNode.FNamespaceURI = namespaceURI + elNode.childNodes = @[] + elNode.attributes = @[] + + elNode.FNodeType = ElementNode + + return elNode + +proc createProcessingInstruction*(doc: PDocument, target: string, data: string): PProcessingInstruction = + ##Creates a ProcessingInstruction node given the specified name and data strings. + + #Check if name contains illegal characters + if illegalChars in target: + raise newException(EInvalidCharacterErr, "Invalid character") + + var PI: PProcessingInstruction + new(PI) + PI.FTarget = target + PI.data = data + PI.FNodeType = ProcessingInstructionNode + return PI + +proc createTextNode*(doc: PDocument, data: string): PText = #Propably TextNode + ##Creates a Text node given the specified string. + var txtNode: PText + new(txtNode) + txtNode.data = data + txtNode.nodeValue = data + txtNode.FNodeName = "#text" + + txtNode.FNodeType = TextNode + return txtNode + +discard """proc getElementById*(doc: PDocument, elementId: string): PElement = + ##Returns the ``Element`` whose ID is given by ``elementId``. If no such element exists, returns ``nil`` + #TODO""" + +proc getElementsByTagName*(doc: PDocument, tagName: string): seq[PNode] = + ##Returns a NodeList of all the Elements with a given tag name in + ##the order in which they are encountered in a preorder traversal of the Document tree. + var result: seq[PNode] = @[] + if doc.FDocumentElement.FNodeName == tagName or tagName == "*": + result.add(doc.FDocumentElement) + + result.add(doc.FDocumentElement.findNodes(tagName)) + return result + +proc getElementsByTagNameNS*(doc: PDocument, namespaceURI: string, localName: string): seq[PNode] = + ##Returns a NodeList of all the Elements with a given localName and namespaceURI + ##in the order in which they are encountered in a preorder traversal of the Document tree. + var result: seq[PNode] = @[] + if doc.FDocumentElement.FLocalName == localName or localName == "*": + if doc.FDocumentElement.FNamespaceURI == namespaceURI or namespaceURI == "*": + result.add(doc.FDocumentElement) + + result.add(doc.FDocumentElement.findNodesNS(namespaceURI, localName)) + return result + +proc importNode*(doc: PDocument, importedNode: PNode, deep: bool): PNode = + ## Imports a node from another document to this document + case importedNode.FNodeType + of AttributeNode: + var nAttr: PAttr = PAttr(importedNode) + nAttr.FOwnerDocument = doc + nAttr.FParentNode = nil + nAttr.FOwnerElement = nil + nAttr.FSpecified = True + return nAttr + of DocumentFragmentNode: + var n: PNode + new(n) + n = importedNode + n.FOwnerDocument = doc + n.FParentNode = nil + + n.FOwnerDocument = doc + n.FParentNode = nil + var tmp: seq[PNode] = n.childNodes + n.childNodes = @[] + if deep == True: + for i in low(tmp.len())..high(tmp.len()): + n.childNodes.add(importNode(doc, tmp[i], deep)) + + return n + of ElementNode: + var n: PNode + new(n) + n = importedNode + n.FOwnerDocument = doc + n.FParentNode = nil + + var tmpA: seq[PAttr] = n.attributes + n.attributes = @[] + # Import the Element node's attributes + for i in low(tmpA.len())..high(tmpA.len()): + n.attributes.add(PAttr(importNode(doc, tmpA[i], deep))) + # Import the childNodes + var tmp: seq[PNode] = n.childNodes + n.childNodes = @[] + if deep == True: + for i in low(tmp.len())..high(tmp.len()): + n.childNodes.add(importNode(doc, tmp[i], deep)) + + return n + of ProcessingInstructionNode, TextNode, CDataSectionNode, CommentNode: + var n: PNode + new(n) + n = importedNode + n.FOwnerDocument = doc + n.FParentNode = nil + return n + else: + raise newException(ENotSupportedErr, "The type of node being imported is not supported") + + +# Node +# Attributes +proc Attributes*(n: PNode): seq[PAttr] = + if n.attributes == nil: n.attributes = @[] # Initialize the sequence if it's nil + return n.attributes + +proc firstChild*(n: PNode): PNode = + if n.childNodes.len() > 0: + return n.childNodes[0] + else: + return nil + +proc lastChild*(n: PNode): PNode = + if n.childNodes.len() > 0: + return n.childNodes[n.childNodes.len() - 1] + else: + return nil + +proc localName*(n: PNode): string = + return n.FLocalName + +proc namespaceURI*(n: PNode): string = + return n.FNamespaceURI + +proc nextSibling*(n: PNode): PNode = + var nLow: int = low(n.FParentNode.childNodes) + var nHigh: int = high(n.FParentNode.childNodes) + for i in nLow..nHigh: + if n.FParentNode.childNodes[i] == n: # HAVE TO TEST this line, not sure if ``==`` will work + return n.FParentNode.childNodes[i + 1] + return nil + +proc nodeName*(n: PNode): string = + return n.FNodeName + +proc nodeType*(n: PNode): int = + return n.FNodeType + +proc ownerDocument*(n: PNode): PDocument = + return n.FOwnerDocument + +proc parentNode*(n: PNode): PNode = + return n.FParentNode + +proc previousSibling*(n: PNode): PNode = + var nLow: int = low(n.FParentNode.childNodes) + var nHigh: int = high(n.FParentNode.childNodes) + for i in nLow..nHigh: + if n.FParentNode.childNodes[i] == n: # HAVE TO TEST this line, not sure if ``==`` will work + return n.FParentNode.childNodes[i - 1] + return nil + +proc `prefix=`*(n: var PNode, value: string) = + # Setter + # Check if name contains illegal characters + if illegalChars in value: + raise newException(EInvalidCharacterErr, "Invalid character") + + if n.FNamespaceURI == nil: + raise newException(ENamespaceErr, "namespaceURI cannot be nil") + elif value.toLower() == "xml" and n.FNamespaceURI != "http://www.w3.org/XML/1998/namespace": + raise newException(ENamespaceErr, + "When the namespace prefix is \"xml\" namespaceURI has to be \"http://www.w3.org/XML/1998/namespace\"") + elif value.toLower() == "xmlns" and n.FNamespaceURI != "http://www.w3.org/2000/xmlns/": + raise newException(ENamespaceErr, + "When the namespace prefix is \"xmlns\" namespaceURI has to be \"http://www.w3.org/2000/xmlns/\"") + elif value.toLower() == "xmlns" and n.FNodeType == AttributeNode: + raise newException(ENamespaceErr, "An AttributeNode cannot have a prefix of \"xmlns\"") + + n.FNodeName = value & ":" & n.FLocalName + if n.nodeType == ElementNode: + var el: PElement = PElement(n) + el.FTagName = value & ":" & n.FLocalName + n = PNode(el) + elif n.nodeType == AttributeNode: + var attr: PAttr = PAttr(n) + attr.FName = value & ":" & n.FLocalName + n = PNode(attr) + +# Procedures +proc appendChild*(n: PNode, newChild: PNode) = + ## Adds the node newChild to the end of the list of children of this node. + ## If the newChild is already in the tree, it is first removed. + + # TODO - Check if n contains newChild + # TODO - Exceptions + + # Check if newChild is from this nodes document + if n.FOwnerDocument != newChild.FOwnerDocument: + raise newException(EWrongDocumentErr, "This node belongs to a different document, use importNode.") + + if n == newChild: + raise newException(EHierarchyRequestErr, "You can't add a node into itself") + + if n.childNodes == nil: n.childNodes = @[] + + newChild.FParentNode = n + for i in low(n.childNodes)..high(n.childNodes): + if n.childNodes[i] == newChild: + n.childNodes[i] = newChild + + n.childNodes.add(newChild) + +proc cloneNode*(n: PNode, deep: bool): PNode = + ## Returns a duplicate of this node, if ``deep`` is `true`, Element node's children are copied + case n.FNodeType + of AttributeNode: + var newNode: PAttr + new(newNode) + newNode = PAttr(n) + newNode.FSpecified = True + newNode.FOwnerElement = nil + return newNode + of ElementNode: + var newNode: PElement + new(newNode) + newNode = PElement(n) + # Import the childNodes + var tmp: seq[PNode] = n.childNodes + n.childNodes = @[] + if deep == True: + for i in low(tmp.len())..high(tmp.len()): + n.childNodes.add(cloneNode(tmp[i], deep)) + return newNode + else: + var newNode: PNode + new(newNode) + newNode = n + return newNode + +proc hasAttributes*(n: PNode): bool = + ## Returns whether this node (if it is an element) has any attributes. + return n.attributes.len() > 0 + +proc hasChildNodes*(n: PNode): bool = + ## Returns whether this node has any children. + return n.childNodes.len() > 0 + +proc insertBefore*(n: PNode, newChild: PNode, refChild: PNode): PNode = + ## Inserts the node ``newChild`` before the existing child node ``refChild``. + ## If ``refChild`` is nil, insert ``newChild`` at the end of the list of children. + + # Check if newChild is from this nodes document + if n.FOwnerDocument != newChild.FOwnerDocument: + raise newException(EWrongDocumentErr, "This node belongs to a different document, use importNode.") + + for i in low(n.childNodes)..high(n.childNodes): + if n.childNodes[i] == refChild: + n.childNodes.insert(newChild, i - 1) + return + +proc isSupported*(n: PNode, feature: string, version: string): bool = + ## Tests whether the DOM implementation implements a specific + ## feature and that feature is supported by this node. + return n.FOwnerDocument.FImplementation.hasFeature(feature, version) + +proc normalize*(n: PNode) = + ## Puts all Text nodes in the full depth of the sub-tree underneath this Node + + # TODO + +proc removeChild*(n: PNode, oldChild: PNode): PNode = + ## Removes the child node indicated by ``oldChild`` from the list of children, and returns it. + for i in low(n.childNodes)..high(n.childNodes): + if n.childNodes[i] == oldChild: + result = n.childNodes[i] + n.childNodes.delete(i) + return result + + raise newException(ENotFoundErr, "Node not found") + +proc replaceChild*(n: PNode, newChild: PNode, oldChild: PNode): PNode = + ## Replaces the child node ``oldChild`` with ``newChild`` in the list of children, and returns the ``oldChild`` node. + + # Check if newChild is from this nodes document + if n.FOwnerDocument != newChild.FOwnerDocument: + raise newException(EWrongDocumentErr, "This node belongs to a different document, use importNode.") + + for i in low(n.childNodes)..high(n.childNodes): + if n.childNodes[i] == oldChild: + result = n.childNodes[i] + n.childNodes[i] = newChild + return result + + raise newException(ENotFoundErr, "Node not found") + +# NamedNodeMap + +proc getNamedItem*(NList: seq[PNode], name: string): PNode = + ## Retrieves a node specified by ``name``. If this node cannot be found returns ``nil`` + for i in items(NList): + if i.nodeName() == name: + return i + return nil + +proc getNamedItem*(NList: seq[PAttr], name: string): PAttr = + ## Retrieves a node specified by ``name``. If this node cannot be found returns ``nil`` + for i in items(NList): + if i.nodeName() == name: + return i + return nil + +proc getNamedItemNS*(NList: seq[PNode], namespaceURI: string, localName: string): PNode = + ## Retrieves a node specified by ``localName`` and ``namespaceURI``. If this node cannot be found returns ``nil`` + for i in items(NList): + if i.namespaceURI() == namespaceURI and i.localName() == localName: + return i + return nil + +proc getNamedItemNS*(NList: seq[PAttr], namespaceURI: string, localName: string): PAttr = + ## Retrieves a node specified by ``localName`` and ``namespaceURI``. If this node cannot be found returns ``nil`` + for i in items(NList): + if i.NamespaceURI() == namespaceURI and i.LocalName() == localName: + return i + return nil + +proc item*(NList: seq[PNode], index: int): PNode = + ## Returns the ``index`` th item in the map. + ## If ``index`` is greater than or equal to the number of nodes in this map, this returns ``nil``. + if index >= NList.len(): return nil + else: return NList[index] + +proc removeNamedItem*(NList: var seq[PNode], name: string): PNode = + ## Removes a node specified by ``name`` + ## Raises the ``ENotFoundErr`` exception, if the node was not found + for i in low(NList)..high(NList): + if NList[i].FNodeName == name: + result = NList[i] + NList.delete(i) + return result + + raise newException(ENotFoundErr, "Node not found") + +proc removeNamedItemNS*(NList: var seq[PNode], namespaceURI: string, localName: string): PNode = + ## Removes a node specified by local name and namespace URI + for i in low(NList)..high(NList): + if NList[i].FLocalName == localName and NList[i].FNamespaceURI == namespaceURI: + result = NList[i] + NList.delete(i) + return result + + raise newException(ENotFoundErr, "Node not found") + +proc setNamedItem*(NList: var seq[PNode], arg: PNode): PNode = + ## Adds ``arg`` as a ``Node`` to the ``NList`` + ## If a node with the same name is already present in this map, it is replaced by the new one. + if NList != nil: + if NList.len() > 0: + #Check if newChild is from this nodes document + if NList[0].FOwnerDocument != arg.FOwnerDocument: + raise newException(EWrongDocumentErr, "This node belongs to a different document, use importNode.") + #Exceptions End + + var item: PNode = NList.getNamedItem(arg.NodeName()) + if item == nil: + NList.add(arg) + return nil + else: + # Node with the same name exists + var index: int = 0 + for i in low(NList)..high(NList): + if NList[i] == item: + index = i + break + NList[index] = arg + return item # Return the replaced node + +proc setNamedItem*(NList: var seq[PAttr], arg: PAttr): PAttr = + ## Adds ``arg`` as a ``Node`` to the ``NList`` + ## If a node with the same name is already present in this map, it is replaced by the new one. + if NList != nil: + if NList.len() > 0: + # Check if newChild is from this nodes document + if NList[0].FOwnerDocument != arg.FOwnerDocument: + raise newException(EWrongDocumentErr, "This node belongs to a different document, use importNode.") + + if arg.FOwnerElement != nil: + raise newException(EInuseAttributeErr, "This attribute is in use by another element, use cloneNode") + + # Exceptions end + var item: PAttr = NList.getNamedItem(arg.nodeName()) + if item == nil: + NList.add(arg) + return nil + else: + # Node with the same name exists + var index: int = 0 + for i in low(NList)..high(NList): + if NList[i] == item: + index = i + break + NList[index] = arg + return item # Return the replaced node + +proc setNamedItemNS*(NList: var seq[PNode], arg: PNode): PNode = + ## Adds a node using its ``namespaceURI`` and ``localName`` + if NList != nil: + if NList.len() > 0: + # Check if newChild is from this nodes document + if NList[0].FOwnerDocument != arg.FOwnerDocument: + raise newException(EWrongDocumentErr, "This node belongs to a different document, use importNode.") + #Exceptions end + + var item: PNode = NList.getNamedItemNS(arg.namespaceURI(), arg.localName()) + if item == nil: + NList.add(arg) + return nil + else: + # Node with the same name exists + var index: int = 0 + for i in low(NList)..high(NList): + if NList[i] == item: + index = i + break + NList[index] = arg + return item # Return the replaced node + +proc setNamedItemNS*(NList: var seq[PAttr], arg: PAttr): PAttr = + ## Adds a node using its ``namespaceURI`` and ``localName`` + if NList != nil: + if NList.len() > 0: + # Check if newChild is from this nodes document + if NList[0].FOwnerDocument != arg.FOwnerDocument: + raise newException(EWrongDocumentErr, "This node belongs to a different document, use importNode.") + + if arg.FOwnerElement != nil: + raise newException(EInuseAttributeErr, "This attribute is in use by another element, use cloneNode") + + # Exceptions end + var item: PAttr = NList.getNamedItemNS(arg.namespaceURI(), arg.localName()) + if item == nil: + NList.add(arg) + return nil + else: + # Node with the same name exists + var index: int = 0 + for i in low(NList)..high(NList): + if NList[i] == item: + index = i + break + NList[index] = arg + return item # Return the replaced node + +# TODO - Maybe implement a ChildlessNode!^ + +# CharacterData - Decided to implement this, +# Didn't add the procedures, because you can just edit .data + +# Attr +# Attributes +proc name*(a: PAttr): string = + return a.FName + +proc specified*(a: PAttr): bool = + return a.FSpecified + +proc ownerElement*(a: PAttr): PElement = + return a.FOwnerElement + +# Element +# Attributes + +proc tagName*(el: PElement): string = + return el.FTagName + +# Procedures +proc getAttribute*(el: PElement, name: string): string = + ## Retrieves an attribute value by ``name`` + var attribute = el.attributes.getNamedItem(name) + if attribute != nil: + return attribute.value + else: + return nil + +proc getAttributeNS*(el: PElement, namespaceURI: string, localName: string): string = + ## Retrieves an attribute value by ``localName`` and ``namespaceURI`` + var attribute = el.attributes.getNamedItemNS(namespaceURI, localName) + if attribute != nil: + return attribute.value + else: + return nil + +proc getAttributeNode*(el: PElement, name: string): PAttr = + ## Retrieves an attribute node by ``name`` + ## To retrieve an attribute node by qualified name and namespace URI, use the `getAttributeNodeNS` method + return el.attributes.getNamedItem(name) + +proc getAttributeNodeNS*(el: PElement, namespaceURI: string, localName: string): PAttr = + ## Retrieves an `Attr` node by ``localName`` and ``namespaceURI`` + return el.attributes.getNamedItemNS(namespaceURI, localName) + +proc getElementsByTagName*(el: PElement, name: string): seq[PNode] = + ## Returns a `NodeList` of all descendant `Elements` of ``el`` with a given tag ``name``, + ## in the order in which they are encountered in a preorder traversal of this `Element` tree + ## If ``name`` is `*`, returns all descendant of ``el`` + result = el.findNodes(name) + +proc getElementsByTagNameNS*(el: PElement, namespaceURI: string, localName: string): seq[PNode] = + ## Returns a `NodeList` of all the descendant Elements with a given + ## ``localName`` and ``namespaceURI`` in the order in which they are + ## encountered in a preorder traversal of this Element tree + result = el.findNodesNS(namespaceURI, localName) + +proc hasAttribute*(el: PElement, name: string): bool = + ## Returns ``true`` when an attribute with a given ``name`` is specified + ## on this element , ``false`` otherwise. + return el.attributes.getNamedItem(name) != nil + +proc hasAttributeNS*(el: PElement, namespaceURI: string, localName: string): bool = + ## Returns ``true`` when an attribute with a given ``localName`` and + ## ``namespaceURI`` is specified on this element , ``false`` otherwise + return el.attributes.getNamedItemNS(namespaceURI, localName) != nil + +proc removeAttribute*(el: PElement, name: string) = + ## Removes an attribute by ``name`` + for i in low(el.attributes)..high(el.attributes): + if el.attributes[i].FName == name: + el.attributes.delete(i) + +proc removeAttributeNS*(el: PElement, namespaceURI: string, localName: string) = + ## Removes an attribute by ``localName`` and ``namespaceURI`` + for i in low(el.attributes)..high(el.attributes): + if el.attributes[i].FNamespaceURI == namespaceURI and + el.attributes[i].FLocalName == localName: + el.attributes.delete(i) + +proc removeAttributeNode*(el: PElement, oldAttr: PAttr): PAttr = + ## Removes the specified attribute node + ## If the attribute node cannot be found raises ``ENotFoundErr`` + for i in low(el.attributes)..high(el.attributes): + if el.attributes[i] == oldAttr: + result = el.attributes[i] + el.attributes.delete(i) + return result + + raise newException(ENotFoundErr, "oldAttr is not a member of el's Attributes") + +proc setAttributeNode*(el: PElement, newAttr: PAttr): PAttr = + ## Adds a new attribute node, if an attribute with the same `nodeName` is + ## present, it is replaced by the new one and the replaced attribute is + ## returned, otherwise ``nil`` is returned. + + # Check if newAttr is from this nodes document + if el.FOwnerDocument != newAttr.FOwnerDocument: + raise newException(EWrongDocumentErr, + "This node belongs to a different document, use importNode.") + + if newAttr.FOwnerElement != nil: + raise newException(EInuseAttributeErr, + "This attribute is in use by another element, use cloneNode") + # Exceptions end + + if el.attributes == nil: el.attributes = @[] + return el.attributes.setNamedItem(newAttr) + +proc setAttributeNodeNS*(el: PElement, newAttr: PAttr): PAttr = + ## Adds a new attribute node, if an attribute with the localName and + ## namespaceURI of ``newAttr`` is present, it is replaced by the new one + ## and the replaced attribute is returned, otherwise ``nil`` is returned. + + # Check if newAttr is from this nodes document + if el.FOwnerDocument != newAttr.FOwnerDocument: + raise newException(EWrongDocumentErr, + "This node belongs to a different document, use importNode.") + + if newAttr.FOwnerElement != nil: + raise newException(EInuseAttributeErr, + "This attribute is in use by another element, use cloneNode") + # Exceptions end + + if el.attributes == nil: el.attributes = @[] + return el.attributes.setNamedItemNS(newAttr) + +proc setAttribute*(el: PElement, name: string, value: string) = + ## Adds a new attribute, as specified by ``name`` and ``value`` + ## If an attribute with that name is already present in the element, its + ## value is changed to be that of the value parameter + ## Raises the EInvalidCharacterErr if the specified ``name`` contains + ## illegal characters + var AttrNode = el.FOwnerDocument.createAttribute(name) + # Check if name contains illegal characters + if illegalChars in name: + raise newException(EInvalidCharacterErr, "Invalid character") + + discard el.setAttributeNode(AttrNode) + # Set the info later, the setAttributeNode checks + # if FOwnerElement is nil, and if it isn't it raises an exception + AttrNode.FOwnerElement = el + AttrNode.FSpecified = True + AttrNode.value = value + +proc setAttributeNS*(el: PElement, namespaceURI, localName, value: string) = + ## Adds a new attribute, as specified by ``namespaceURI``, ``localName`` + ## and ``value``. + + # Check if name contains illegal characters + if illegalChars in namespaceURI or illegalChars in localName: + raise newException(EInvalidCharacterErr, "Invalid character") + + var AttrNode = el.FOwnerDocument.createAttributeNS(namespaceURI, localName) + + discard el.setAttributeNodeNS(AttrNode) + # Set the info later, the setAttributeNode checks + # if FOwnerElement is nil, and if it isn't it raises an exception + AttrNode.FOwnerElement = el + AttrNode.FSpecified = True + AttrNode.value = value + +# Text +proc splitData*(TextNode: PText, offset: int): PText = + ## Breaks this node into two nodes at the specified offset, + ## keeping both in the tree as siblings. + + # TODO - need insert(seq[T]) + +# ProcessingInstruction +proc target*(PI: PProcessingInstruction): string = + return PI.FTarget + + +# --Other stuff-- +# Writer +proc nodeToXml(n: PNode, indent: int = 0): string = + result = repeatChar(indent, ' ') & "<" & n.nodeName + for i in items(n.Attributes): + result.add(" " & i.name & "=\"" & i.value & "\"") + + if n.childNodes.len() == 0: + result.add("/>") # No idea why this doesn't need a \n :O + else: + # End the beginning of this tag + result.add(">\n") + for i in items(n.childNodes): + case i.nodeType + of ElementNode: + result.add(nodeToXml(i, indent + 2)) + of TextNode: + result.add(repeatChar(indent * 2, ' ')) + result.add(i.nodeValue) + of CDataSectionNode: + result.add(repeatChar(indent * 2, ' ')) + result.add("<![CDATA[" & i.nodeValue & "]]>") + of ProcessingInstructionNode: + result.add(repeatChar(indent * 2, ' ')) + result.add("<?" & PProcessingInstruction(i).target & " " & + PProcessingInstruction(i).data & " ?>") + of CommentNode: + result.add(repeatChar(indent * 2, ' ')) + result.add("<!-- " & i.nodeValue & " -->") + else: + continue + result.add("\n") + # Add the ending tag - </tag> + result.add(repeatChar(indent, ' ') & "</" & n.nodeName & ">") + +proc `$`*(doc: PDocument): string = + ## Converts a PDocument object into a string representation of it's XML + result = "<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n" + result.add(nodeToXml(doc.documentElement)) diff --git a/lib/pure/xmldomparser.nim b/lib/pure/xmldomparser.nim new file mode 100644 index 000000000..90d4d85b1 --- /dev/null +++ b/lib/pure/xmldomparser.nim @@ -0,0 +1,110 @@ +# +# +# Nimrod's Runtime Library +# (c) Copyright 2010 Dominik Picheta +# +# See the file "copying.txt", included in this +# distribution, for details about the copyright. +# + +import xmldom, os, streams, parsexml, strutils + +## This module parses a XML Document into a XML DOM Document representation. + +#XMLDom's Parser - Turns XML into a Document + +type + #Parsing errors + EMismatchedTag* = object of E_Base ## Raised when a tag is not properly closed + +template newException(exceptn, message: expr): expr = + block: # open a new scope + var + e: ref exceptn + new(e) + e.msg = message + e + +proc parseText(x: var TXmlParser, doc: var PDocument): PText = + result = doc.createTextNode(x.charData()) + +proc parseElement(x: var TXmlParser, doc: var PDocument): PElement = + var n = doc.createElement("") + + while True: + case x.kind() + of xmlEof: + break + of xmlElementStart: + if n.tagName() != "": + n.appendChild(parseElement(x, doc)) + else: + n = doc.createElement(x.elementName) + of xmlElementOpen: + if n.tagName() != "": + n.appendChild(parseElement(x, doc)) + else: + if x.elementName.contains(':'): + #TODO: NamespaceURI + n = doc.createElementNS("nil", x.elementName) + else: + n = doc.createElement(x.elementName) + + of xmlElementEnd: + if x.elementName == n.nodeName: + return n + else: #The wrong element is ended + raise newException(EMismatchedTag, "Mismatched tag at line " & + $x.getLine() & " column " & $x.getColumn) + + of xmlCharData: + n.appendChild(parseText(x, doc)) + of xmlAttribute: + if x.attrKey.contains(':'): + #TODO: NamespaceURI + n.setAttributeNS("nil", x.attrKey, x.attrValue) + else: + n.setAttribute(x.attrKey, x.attrValue) + of xmlCData: + n.appendChild(doc.createCDATASection(x.charData())) + of xmlComment: + n.appendChild(doc.createComment(x.charData())) + of xmlPI: + n.appendChild(doc.createProcessingInstruction(x.PIName(), x.PIRest())) + else: + # echo(x.kind()) # XXX do nothing here!? + x.next() + + raise newException(EMismatchedTag, + "Mismatched tag at line " & $x.getLine() & " column " & $x.getColumn) + +proc loadXML*(path: string): PDocument = + ## Loads and parses XML from file specified by ``path``, and returns + ## a ``PDocument`` + + var s = newFileStream(path, fmRead) + if s == nil: raise newException(EIO, "Unable to read file " & path) + + var x: TXmlParser + open(x, s, path, {reportComments}) + + var XmlDoc: PDocument + var DOM: PDOMImplementation = getDOM() + + while True: + x.next() + case x.kind() + of xmlEof: + break + of xmlElementStart, xmlElementOpen: + var el: PElement = parseElement(x, XmlDoc) + XmlDoc = dom.createDocument(el) + else: + # echo(x.kind()) + + return XmlDoc + + +when isMainModule: + var xml = loadXML(r"C:\Users\Dominik\Desktop\Code\Nimrod\xmldom\test.xml") + echo($xml) diff --git a/web/news.txt b/web/news.txt index cea6bc124..096ee8ba9 100755 --- a/web/news.txt +++ b/web/news.txt @@ -34,6 +34,8 @@ Additions - Added ``httpclient`` module. - Added ``parseutils`` module. - Added ``unidecode`` module. +- Added ``xmldom`` module. +- Added ``xmldomparser`` module. - Many wrappers now do not contain redundant name prefixes (like ``GTK_``, ``lua``). The new wrappers are available in ``lib/newwrap``. Change your configuration file to use these. diff --git a/web/nimrod.ini b/web/nimrod.ini index af2d0c4b7..1cb494f9c 100755 --- a/web/nimrod.ini +++ b/web/nimrod.ini @@ -30,9 +30,9 @@ srcdoc: "pure/parsecfg;pure/parsexml;pure/parsecsv;pure/parsesql" srcdoc: "pure/streams;pure/terminal;pure/cgi;impure/web;pure/unicode" srcdoc: "impure/zipfiles;pure/xmlgen;pure/macros;pure/parseutils;pure/browsers" srcdoc: "impure/db_postgres;impure/db_mysql;pure/httpserver;pure/httpclient" -srcdoc: "pure/ropes" +srcdoc: "pure/ropes;pure/unidecode/unidecode;pure/xmldom;pure/xmldomparser" -webdoc: "wrappers/libcurl;pure/md5;wrappers/mysql" +webdoc: "wrappers/libcurl;pure/md5;wrappers/mysql;wrappers/iup" webdoc: "wrappers/sqlite3;wrappers/python;wrappers/tcl" webdoc: "posix/posix;wrappers/odbcsql;impure/dialogs" |