def compile(self, source, dest, is_two_file=True, post=None, lang=None):
"""Compile the source file into HTML and save as dest."""
makedirs(os.path.dirname(dest))
if mw is None:
req_missing(['smc.mw'],
'build this site (compile with MediaWiki)',
python=True)
with io.open(dest, "w+", encoding="utf8") as out_file:
with io.open(source, "r", encoding="utf8") as in_file:
data = in_file.read()
if not is_two_file:
data = re.split('(\n\n|\r\n\r\n)', data, maxsplit=1)[-1]
parser = mw.Parser(parseinfo=False, whitespace='', nameguard=False)
ast = parser.parse(data,
'document',
semantics=mw.Semantics(parser))
output = etree.tostring(ast, encoding='utf8').decode('utf8')
output, shortcode_deps = self.site.apply_shortcodes(
output,
filename=source,
with_dependencies=True,
extra_context=dict(post=post))
out_file.write(output)
if post is None:
if shortcode_deps:
self.logger.error(
"Cannot save dependencies for post {0} (post unknown)",
source)
else:
post._depfile[dest] += shortcode_deps
def compile_string(self,
data,
source_path=None,
is_two_file=True,
post=None,
lang=None):
"""Compile the source file into HTML strings (with shortcode support).
Returns a tuple of at least two elements: HTML string [0] and shortcode dependencies [last].
"""
if mw is None:
req_missing(['smc.mw'],
'build this site (compile with MediaWiki)',
python=True)
if not is_two_file:
_, data = self.split_metadata(data, post, lang)
new_data, shortcodes = sc.extract_shortcodes(data)
parser = mw.Parser(parseinfo=False, whitespace='', nameguard=False)
ast = parser.parse(new_data,
'document',
semantics=mw.Semantics(parser))
output = etree.tostring(ast, encoding='utf8').decode('utf8')
output, shortcode_deps = self.site.apply_shortcodes_uuid(
output,
shortcodes,
filename=source_path,
extra_context={'post': post})
return output, shortcode_deps
def run_parser(text, filename=None, start=None, profile_data=None,
trace=False, headings=None):
if start is None:
start = "document"
parser = mw.Parser(parseinfo=False, whitespace='', nameguard=False)
ast = parser.parse(text, start, filename=filename,
semantics=mw.Semantics(parser, headings=headings), trace=trace,
nameguard=False, whitespace='')
if sys.version < '3':
text = etree.tostring(ast)
else:
text = etree.tostring(ast, encoding=str)
return text
def compile_html(self, source, dest, is_two_file=True):
makedirs(os.path.dirname(dest))
if mw is None:
req_missing(['smc.mw'],
'build this site (compile with MediaWiki)',
python=True)
with io.open(dest, "w+", encoding="utf8") as out_file:
with io.open(source, "r", encoding="utf8") as in_file:
data = in_file.read()
if not is_two_file:
data = re.split('(\n\n|\r\n\r\n)', data, maxsplit=1)[-1]
parser = mw.Parser(parseinfo=False, whitespace='', nameguard=False)
ast = parser.parse(data,
'document',
semantics=mw.Semantics(parser))
output = etree.tostring(ast, encoding='utf8').decode('utf8')
out_file.write(output)
def parser(self, inp, profile_data=None):
if type(inp) == tuple:
inp, headings = inp
else:
headings = None
parser = mw.Parser(parseinfo=False)
semantics = TestSemantics(parser,
headings=headings,
settings=self._preprocessor.settings)
ast = parser.parse(inp, "document", semantics=semantics, trace=False)
body = ast[0]
if body.text is not None:
text = body.text
else:
text = ""
# ast[0] is "body"
for node in body.getchildren():
# tostring adds tail
text = text + etree.tostring(node).decode("utf-8")
return text