def pisaParser(src, c, default_css="", xhtml=False, encoding=None, xml_output=None):
"""
- Parse HTML and get miniDOM
- Extract CSS informations, add default CSS, parse CSS
- Handle the document DOM itself and build reportlab story
- Return Context object
"""
if xhtml:
parser = html5lib.XHTMLParser(tree=treebuilders.getTreeBuilder("dom"))
else:
parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("dom"))
if type(src) in types.StringTypes:
if type(src) is types.UnicodeType:
encoding = "utf8"
src = src.encode(encoding)
#src = pisaTempFile(src, capacity=c.capacity)
# Test for the restrictions of html5lib
if encoding:
# Workaround for html5lib<0.11.1
if hasattr(inputstream, "isValidEncoding"):
if encoding.strip().lower() == "utf8":
encoding = "utf-8"
if not inputstream.isValidEncoding(encoding):
log.error("%r is not a valid encoding e.g. 'utf8' is not valid but 'utf-8' is!", encoding)
else:
if inputstream.codecName(encoding) is None:
log.error("%r is not a valid encoding", encoding)
#encoding = 'utf-8'
document = parser.parse(
src,
encoding=encoding)
if xml_output:
xml_output.write(document.toprettyxml(encoding="utf8"))
if default_css:
c.addCSS(default_css)
#from html5lib import treewalkers, serializer
#walker = treewalkers.getTreeWalker("dom")
#stream = walker(document)
#s = serializer.htmlserializer.HTMLSerializer(omit_optional_tags=False)
#output_generator = s.serialize(stream)
#for item in output_generator:
# print item
#pisaPreLoop(document, c)
#try:
c.parseCSS()
#except:
# c.cssText = DEFAULT_CSS
# c.parseCSS()
# c.debug(9, pprint.pformat(c.css))
pisaLoop(document, c)
return c
def pisaParser(src, context, default_css="", xhtml=False, encoding=None, xml_output=None):
"""
- Parse HTML and get miniDOM
- Extract CSS informations, add default CSS, parse CSS
- Handle the document DOM itself and build reportlab story
- Return Context object
"""
global CSSAttrCache
CSSAttrCache = {}
if xhtml:
#TODO: XHTMLParser doesn't see to exist...
parser = html5lib.XHTMLParser(tree=treebuilders.getTreeBuilder("dom"))
else:
parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("dom"))
if type(src) in StringTypes:
if type(src) is unicode:
# If an encoding was provided, do not change it.
if not encoding:
encoding = "utf-8"
src = src.encode(encoding)
src = pisaTempFile(src, capacity=context.capacity)
# Test for the restrictions of html5lib
if encoding:
# Workaround for html5lib<0.11.1
if hasattr(inputstream, "isValidEncoding"):
if encoding.strip().lower() == "utf8":
encoding = "utf-8"
if not inputstream.isValidEncoding(encoding):
log.error("%r is not a valid encoding e.g. 'utf8' is not valid but 'utf-8' is!", encoding)
else:
if inputstream.codecName(encoding) is None:
log.error("%r is not a valid encoding", encoding)
document = parser.parse(
src,
encoding=encoding)
if xml_output:
if encoding:
xml_output.write(document.toprettyxml(encoding=encoding))
else:
xml_output.write(document.toprettyxml(encoding="utf8"))
if default_css:
context.addDefaultCSS(default_css)
pisaPreLoop(document, context)
#try:
context.parseCSS()
#except:
# context.cssText = DEFAULT_CSS
# context.parseCSS()
# context.debug(9, pprint.pformat(context.css))
pisaLoop(document, context)
return context
def pisaParser(src, context, default_css="", xhtml=False, encoding=None, xml_output=None):
"""
- Parse HTML and get miniDOM
- Extract CSS informations, add default CSS, parse CSS
- Handle the document DOM itself and build reportlab story
- Return Context object
"""
global CSSAttrCache
CSSAttrCache = {}
if xhtml:
#TODO: XHTMLParser doesn't see to exist...
parser = html5lib.XHTMLParser(tree=treebuilders.getTreeBuilder("dom"))
else:
parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("dom"))
if type(src) in StringTypes:
if type(src) is unicode:
# If an encoding was provided, do not change it.
if not encoding:
encoding = "utf-8"
src = src.encode(encoding)
src = pisaTempFile(src, capacity=context.capacity)
# Test for the restrictions of html5lib
if encoding:
# Workaround for html5lib<0.11.1
if hasattr(inputstream, "isValidEncoding"):
if encoding.strip().lower() == "utf8":
encoding = "utf-8"
if not inputstream.isValidEncoding(encoding):
log.error("%r is not a valid encoding e.g. 'utf8' is not valid but 'utf-8' is!", encoding)
else:
if inputstream.codecName(encoding) is None:
log.error("%r is not a valid encoding", encoding)
document = parser.parse(
src,
encoding=encoding)
if xml_output:
if encoding:
xml_output.write(document.toprettyxml(encoding=encoding))
else:
xml_output.write(document.toprettyxml(encoding="utf8"))
if default_css:
context.addDefaultCSS(default_css)
pisaPreLoop(document, context)
#try:
context.parseCSS()
#except:
# context.cssText = DEFAULT_CSS
# context.parseCSS()
# context.debug(9, pprint.pformat(context.css))
pisaLoop(document, context)
return context
def pisaParser(src, c, default_css="", xhtml=False, encoding=None):
"""
- Parse HTML and get miniDOM
- Extract CSS informations, add default CSS, parse CSS
- Handle the document DOM itself and build reportlab story
- Return Context object
"""
if xhtml:
parser = html5lib.XHTMLParser(tree=treebuilders.getTreeBuilder("dom"))
else:
parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("dom"))
if type(src) in types.StringTypes:
if type(src) is types.UnicodeType:
encoding = "utf8"
src = src.encode(encoding)
src = StringIO.StringIO(src)
# Test for the restrictions of html5lib
if encoding:
# Workaround for html5lib<0.11.1
if hasattr(inputstream, "isValidEncoding"):
if encoding.strip().lower() == "utf8":
encoding = "utf-8"
if not inputstream.isValidEncoding(encoding):
log.error("%r is not a valid encoding e.g. 'utf8' is not valid but 'utf-8' is!", encoding)
else:
if inputstream.codecName(encoding) is None:
log.error("%r is not a valid encoding", encoding)
document = parser.parse(
src,
encoding=encoding)
# print document.toprettyxml()
if default_css:
c.addCSS(default_css)
pisaPreLoop(document, c)
#try:
c.parseCSS()
#except:
# c.cssText = DEFAULT_CSS
# c.parseCSS()
# c.debug(9, pprint.pformat(c.css))
pisaLoop(document, c)
return c
def pisaParser(src, c, default_css="", xhtml=False, encoding=None):
"""
- Parse HTML and get miniDOM
- Extract CSS informations, add default CSS, parse CSS
- Handle the document DOM itself and build reportlab story
- Return Context object
"""
if xhtml:
parser = html5lib.XHTMLParser(tree=treebuilders.getTreeBuilder("dom"))
else:
parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("dom"))
if type(src) in types.StringTypes:
if type(src) is types.UnicodeType:
encoding = "utf8"
src = src.encode(encoding)
src = StringIO.StringIO(src)
# Test for the restrictions of html5lib
if encoding:
# Workaround for html5lib<0.11.1
if hasattr(inputstream, "isValidEncoding"):
if encoding.strip().lower() == "utf8":
encoding = "utf-8"
if not inputstream.isValidEncoding(encoding):
log.error(
"%r is not a valid encoding e.g. 'utf8' is not valid but 'utf-8' is!",
encoding)
else:
if inputstream.codecName(encoding) is None:
log.error("%r is not a valid encoding", encoding)
document = parser.parse(src, encoding=encoding)
# print document.toprettyxml()
if default_css:
c.addCSS(default_css)
pisaPreLoop(document, c)
#try:
c.parseCSS()
#except:
# c.cssText = DEFAULT_CSS
# c.parseCSS()
# c.debug(9, pprint.pformat(c.css))
pisaLoop(document, c)
return c
def test_codec_name(self):
self.assertEquals(inputstream.codecName("utf-8"), "utf-8")
self.assertEquals(inputstream.codecName("utf8"), "utf-8")
self.assertEquals(inputstream.codecName(" utf8 "), "utf-8")
self.assertEquals(inputstream.codecName("ISO_8859--1"), "windows-1252")
def test_codec_name_d(self):
self.assertEqual(inputstream.codecName("ISO_8859--1"), "windows-1252")
def test_codec_name_c(self):
self.assertEqual(inputstream.codecName(" utf8 "), "utf-8")
def test_codec_name_d(self):
self.assertEqual(inputstream.codecName("ISO_8859--1"), "windows-1252")
def test_codec_name_c(self):
self.assertEqual(inputstream.codecName(" utf8 "), "utf-8")
def test_codec_name(self):
self.assertEquals(inputstream.codecName("utf-8"), "utf-8")
self.assertEquals(inputstream.codecName("utf8"), "utf-8")
self.assertEquals(inputstream.codecName(" utf8 "), "utf-8")
self.assertEquals(inputstream.codecName("ISO_8859--1"), "windows-1252")
def test_codec_name_d(self):
self.assertEqual(inputstream.codecName('ISO_8859--1'), 'windows-1252')
def test_codec_name_c(self):
self.assertEqual(inputstream.codecName(' utf8 '), 'utf-8')
def test_codec_name_a(self):
self.assertEqual(inputstream.codecName(u"utf-8"), u"utf-8")