Paul Prescod <paul@prescod.net>:

SAX interfaces for Python.

1 files changed, 270 insertions, 0 deletions

diff --git a/Lib/xml/sax/handler.py b/Lib/xml/sax/handler.py
new file mode 100644
index 0000000..cbbb959
--- /dev/null
+++ b/Lib/xml/sax/handler.py
@@ -0,0 +1,270 @@
+"""
+This module contains the core classes of version 2.0 of SAX for Python.
+This file provides only default classes with absolutely minimum
+functionality, from which drivers and applications can be subclassed.
+
+Many of these classes are empty and are included only as documentation
+of the interfaces.
+
+$Id$
+"""
+
+version = '2.0beta'
+#============================================================================
+#
+# HANDLER INTERFACES
+#
+#============================================================================
+# ===== ErrorHandler =====
+class ErrorHandler:
+    """Basic interface for SAX error handlers. If you create an object
+    that implements this interface, then register the object with your
+    Parser, the parser will call the methods in your object to report
+    all warnings and errors. There are three levels of errors
+    available: warnings, (possibly) recoverable errors, and
+    unrecoverable errors. All methods take a SAXParseException as the
+    only parameter."""
+
+    def error(self, exception):
+	"Handle a recoverable error."
+        raise exception
+
+    def fatalError(self, exception):
+	"Handle a non-recoverable error."
+        raise exception
+
+    def warning(self, exception):
+	"Handle a warning."   
+        print exception
+
+# ===== CONTENTHANDLER =====
+
+class ContentHandler:
+    """Interface for receiving logical document content events.
+
+    This is the main callback interface in SAX, and the one most
+    important to applications. The order of events in this interface
+    mirrors the order of the information in the document."""
+
+    def __init__(self):
+        self._locator = None
+    
+    def setDocumentLocator(self, locator):
+        """Called by the parser to give the application a locator for
+        locating the origin of document events.
+
+        SAX parsers are strongly encouraged (though not absolutely
+        required) to supply a locator: if it does so, it must supply
+        the locator to the application by invoking this method before
+        invoking any of the other methods in the DocumentHandler
+        interface.
+
+        The locator allows the application to determine the end
+        position of any document-related event, even if the parser is
+        not reporting an error. Typically, the application will use
+        this information for reporting its own errors (such as
+        character content that does not match an application's
+        business rules). The information returned by the locator is
+        probably not sufficient for use with a search engine.
+        
+        Note that the locator will return correct information only
+        during the invocation of the events in this interface. The
+        application should not attempt to use it at any other time."""
+        self._locator = locator        
+
+    def startDocument(self):
+        """Receive notification of the beginning of a document.
+        
+        The SAX parser will invoke this method only once, before any
+        other methods in this interface or in DTDHandler (except for
+        setDocumentLocator)."""
+
+    def endDocument(self):
+        """Receive notification of the end of a document.
+        
+        The SAX parser will invoke this method only once, and it will
+        be the last method invoked during the parse. The parser shall
+        not invoke this method until it has either abandoned parsing
+        (because of an unrecoverable error) or reached the end of
+        input."""
+
+    def startPrefixMapping(self, prefix, uri):
+        """Begin the scope of a prefix-URI Namespace mapping.
+        
+        The information from this event is not necessary for normal
+        Namespace processing: the SAX XML reader will automatically
+        replace prefixes for element and attribute names when the
+        http://xml.org/sax/features/namespaces feature is true (the
+        default).
+        
+        There are cases, however, when applications need to use
+        prefixes in character data or in attribute values, where they
+        cannot safely be expanded automatically; the
+        start/endPrefixMapping event supplies the information to the
+        application to expand prefixes in those contexts itself, if
+        necessary.
+
+        Note that start/endPrefixMapping events are not guaranteed to
+        be properly nested relative to each-other: all
+        startPrefixMapping events will occur before the corresponding
+        startElement event, and all endPrefixMapping events will occur
+        after the corresponding endElement event, but their order is
+        not guaranteed."""
+
+    def endPrefixMapping(self, prefix):
+        """End the scope of a prefix-URI mapping.
+        
+        See startPrefixMapping for details. This event will always
+        occur after the corresponding endElement event, but the order
+        of endPrefixMapping events is not otherwise guaranteed."""
+
+    def startElement(self, name, attrs):
+        """Signals the start of an element.
+
+        The name parameter contains the name of the element type as a
+        (uri ,localname) tuple, the qname parameter the raw XML 1.0
+        name used in the source document, and the attrs parameter
+        holds an instance of the Attributes class containing the
+        attributes of the element."""
+
+    def endElement(self, name ):
+        """Signals the end of an element.
+
+        The name parameter contains the name of the element type, just
+        as with the startElement event."""
+
+    def characters(self, content):
+        """Receive notification of character data.
+        
+        The Parser will call this method to report each chunk of
+        character data. SAX parsers may return all contiguous
+        character data in a single chunk, or they may split it into
+        several chunks; however, all of the characters in any single
+        event must come from the same external entity so that the
+        Locator provides useful information."""
+
+    def ignorableWhitespace(self ):
+        """Receive notification of ignorable whitespace in element content.
+        
+        Validating Parsers must use this method to report each chunk
+        of ignorable whitespace (see the W3C XML 1.0 recommendation,
+        section 2.10): non-validating parsers may also use this method
+        if they are capable of parsing and using content models.
+        
+        SAX parsers may return all contiguous whitespace in a single
+        chunk, or they may split it into several chunks; however, all
+        of the characters in any single event must come from the same
+        external entity, so that the Locator provides useful
+        information.
+        
+        The application must not attempt to read from the array
+        outside of the specified range."""
+
+    def processingInstruction(self, target, data):
+        """Receive notification of a processing instruction.
+        
+        The Parser will invoke this method once for each processing
+        instruction found: note that processing instructions may occur
+        before or after the main document element.
+
+        A SAX parser should never report an XML declaration (XML 1.0,
+        section 2.8) or a text declaration (XML 1.0, section 4.3.1)
+        using this method."""
+
+    def skippedEntity(self, name):
+        """Receive notification of a skipped entity.
+        
+        The Parser will invoke this method once for each entity
+        skipped. Non-validating processors may skip entities if they
+        have not seen the declarations (because, for example, the
+        entity was declared in an external DTD subset). All processors
+        may skip external entities, depending on the values of the
+        http://xml.org/sax/features/external-general-entities and the
+        http://xml.org/sax/features/external-parameter-entities
+        properties."""
+        
+#============================================================================
+#
+# CORE FEATURES
+#
+#============================================================================
+
+feature_namespaces = "http://xml.org/sax/features/namespaces"
+# true: Perform Namespace processing (default).
+# false: Optionally do not perform Namespace processing
+#        (implies namespace-prefixes).
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_namespace_prefixes = "http://xml.org/sax/features/namespace-prefixes"
+# true: Report the original prefixed names and attributes used for Namespace
+#       declarations.
+# false: Do not report attributes used for Namespace declarations, and
+#        optionally do not report original prefixed names (default).
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_string_interning = "http://xml.org/sax/features/string-interning"
+# true: All element names, prefixes, attribute names, Namespace URIs, and
+#       local names are interned using the built-in intern function.
+# false: Names are not necessarily interned, although they may be (default).
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_validation = "http://xml.org/sax/features/validation"
+# true: Report all validation errors (implies external-general-entities and
+#       external-parameter-entities).
+# false: Do not report validation errors.
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_external_ges = "http://xml.org/sax/features/external-general-entities"
+# true: Include all external general (text) entities.
+# false: Do not include external general entities.
+# access: (parsing) read-only; (not parsing) read/write
+
+feature_external_pes = "http://xml.org/sax/features/external-parameter-entities"
+# true: Include all external parameter entities, including the external
+#       DTD subset.
+# false: Do not include any external parameter entities, even the external
+#        DTD subset.
+# access: (parsing) read-only; (not parsing) read/write
+
+all_features = [feature_namespaces,
+                feature_namespace_prefixes,
+                feature_string_interning,
+                feature_validation,
+                feature_external_ges,
+                feature_external_pes]
+
+
+#============================================================================
+#
+# CORE PROPERTIES
+#
+#============================================================================
+
+property_lexical_handler = "http://xml.org/sax/properties/lexical-handler"
+# data type: xml.sax.sax2lib.LexicalHandler
+# description: An optional extension handler for lexical events like comments.
+# access: read/write
+
+property_declaration_handler = "http://xml.org/sax/properties/declaration-handler"
+# data type: xml.sax.sax2lib.DeclHandler
+# description: An optional extension handler for DTD-related events other
+#              than notations and unparsed entities.
+# access: read/write
+
+property_dom_node = "http://xml.org/sax/properties/dom-node"
+# data type: org.w3c.dom.Node
+# description: When parsing, the current DOM node being visited if this is
+#              a DOM iterator; when not parsing, the root DOM node for
+#              iteration.
+# access: (parsing) read-only; (not parsing) read/write
+
+property_xml_string = "http://xml.org/sax/properties/xml-string"
+# data type: String
+# description: The literal string of characters that was the source for
+#              the current event.
+# access: read-only
+
+all_properties = [property_lexical_handler,
+                  property_dom_node,
+                  property_declaration_handler,
+                  property_xml_string]