Added a separate class for XML processing instructions, which have a slightly different format from SGML processing instructions. [bug=1504383]

4 files changed, 19 insertions, 1 deletions

diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py
index 823ca15..b919be4 100644
--- a/bs4/builder/_htmlparser.py
+++ b/bs4/builder/_htmlparser.py
@@ -8,6 +8,7 @@ __all__ = [
     ]
 
 from HTMLParser import HTMLParser
+from pdb import set_trace
 
 try:
     from HTMLParser import HTMLParseError
diff --git a/bs4/builder/_lxml.py b/bs4/builder/_lxml.py
index bfec582..67cdb4c 100644
--- a/bs4/builder/_lxml.py
+++ b/bs4/builder/_lxml.py
@@ -5,6 +5,7 @@ __all__ = [
     'LXMLTreeBuilder',
     ]
 
+from pdb import set_trace
 from io import BytesIO
 from StringIO import StringIO
 import collections
@@ -14,6 +15,7 @@ from bs4.element import (
     Doctype,
     NamespacedAttribute,
     ProcessingInstruction,
+    XMLProcessingInstruction,
 )
 from bs4.builder import (
     FAST,
@@ -105,6 +107,10 @@ class LXMLTreeBuilderForXML(TreeBuilder):
         # iterate over the encodings, and tell lxml to try to parse
         # the document as each one in turn.
         is_html = not self.is_xml
+        if is_html:
+            self.processing_instruction_class = ProcessingInstruction
+        else:
+            self.processing_instruction_class = XMLProcessingInstruction
         try_encodings = [user_specified_encoding, document_declared_encoding]
         detector = EncodingDetector(
             markup, try_encodings, is_html, exclude_encodings)
@@ -203,7 +209,7 @@ class LXMLTreeBuilderForXML(TreeBuilder):
     def pi(self, target, data):
         self.soup.endData()
         self.soup.handle_data(target + ' ' + data)
-        self.soup.endData(ProcessingInstruction)
+        self.soup.endData(self.processing_instruction_class)
 
     def data(self, content):
         self.soup.handle_data(content)
diff --git a/bs4/element.py b/bs4/element.py
index 872ebf6..9e2bfec 100644
--- a/bs4/element.py
+++ b/bs4/element.py
@@ -745,10 +745,16 @@ class CData(PreformattedString):
     SUFFIX = u']]>'
 
 class ProcessingInstruction(PreformattedString):
+    """A SGML processing instruction."""
 
     PREFIX = u'<?'
     SUFFIX = u'>'
 
+class XMLProcessingInstruction(ProcessingInstruction):
+    """An XML processing instruction."""
+    PREFIX = u'<?'
+    SUFFIX = u'?>'
+
 class Comment(PreformattedString):
 
     PREFIX = u'<!--'
diff --git a/bs4/testing.py b/bs4/testing.py
index 4af16f6..1e2cc9c 100644
--- a/bs4/testing.py
+++ b/bs4/testing.py
@@ -565,6 +565,11 @@ class XMLTreeBuilderSmokeTest(object):
         soup = self.soup(markup)
         self.assertEqual(markup, soup.encode("utf8"))
 
+    def test_processing_instruction(self):
+        markup = b"""<?xml version="1.0" encoding="utf8"?>\n<?PITarget PIContent?>"""
+        soup = self.soup(markup)
+        self.assertEqual(markup, soup.encode("utf8"))
+
     def test_real_xhtml_document(self):
         """A real XHTML document should come out *exactly* the same as it went in."""
         markup = b"""<?xml version="1.0" encoding="utf-8"?>