def quoted_val(state, text, i, formats, user_data):
' A quoted attribute value '
quote = '"' if state.parse is DQ_VAL else "'"
add_attr_data(user_data, ATTR_VALUE, ATTR_START, i)
pos = text.find(quote, i)
if pos == -1:
num = len(text) - i
is_link = is_class = False
else:
num = pos - i + 1
state.parse = IN_OPENING_TAG
if state.tag_being_defined is not None and state.attribute_name in ('lang', 'xml:lang'):
try:
state.tag_being_defined.lang = parse_lang_code(text[i:pos])
except ValueError:
pass
add_attr_data(user_data, ATTR_VALUE, ATTR_END, i + num)
is_link = state.attribute_name in LINK_ATTRS
is_class = not is_link and state.attribute_name == 'class'
if is_link:
if verify_link(text[i:i+num - 1], user_data.doc_name) is False:
return [(num - 1, formats['bad_link']), (1, formats['string'])]
return [(num - 1, formats['link']), (1, formats['string'])]
elif is_class:
return [(num - 1, formats['class_attr']), (1, formats['string'])]
return [(num, formats['string'])]
def quoted_val(state, text, i, formats, user_data):
' A quoted attribute value '
quote = '"' if state.parse is DQ_VAL else "'"
add_attr_data(user_data, ATTR_VALUE, ATTR_START, i)
pos = text.find(quote, i)
if pos == -1:
num = len(text) - i
is_link = is_class = False
else:
num = pos - i + 1
state.parse = IN_OPENING_TAG
if state.tag_being_defined is not None and state.attribute_name in (
'lang', 'xml:lang'):
try:
state.tag_being_defined.lang = parse_lang_code(text[i:pos])
except ValueError:
pass
add_attr_data(user_data, ATTR_VALUE, ATTR_END, i + num)
is_link = state.attribute_name in LINK_ATTRS
is_class = not is_link and state.attribute_name == 'class'
if is_link:
if verify_link(text[i:i + num - 1], user_data.doc_name) is False:
return [(num - 1, formats['bad_link']), (1, formats['string'])]
return [(num - 1, formats['link']), (1, formats['string'])]
elif is_class:
return [(num - 1, formats['class_attr']), (1, formats['string'])]
return [(num, formats['string'])]
def content(state, text, i, formats, user_data):
' Inside content blocks '
m = space_pat.match(text, i)
if m is not None:
return [(len(m.group()), None)]
cdo = cdo_pat.match(text, i)
if cdo is not None:
state.parse = IN_COMMENT_CONTENT
return [(len(cdo.group()), formats['comment'])]
if text[i] == '"':
state.parse = IN_DQS
return [(1, formats['string'])]
if text[i] == "'":
state.parse = IN_SQS
return [(1, formats['string'])]
if text[i] == '}':
state.blocks -= 1
state.parse = NORMAL if state.blocks < 1 else IN_CONTENT
return [(1, formats['bracket'])]
if text[i] == '{':
state.blocks += 1
return [(1, formats['bracket'])]
for token, fmt, name in content_tokens:
m = token.match(text, i)
if m is not None:
if name is URL_TOKEN:
h = 'link'
url = m.group()
prefix, main, suffix = url[:4], url[4:-1], url[-1]
if len(main) > 1 and main[0] in ('"',
"'") and main[0] == main[-1]:
prefix += main[0]
suffix = main[-1] + suffix
main = main[1:-1]
h = 'bad_link' if verify_link(
main, user_data.doc_name) is False else 'link'
return [(len(prefix), formats[fmt]), (len(main), formats[h]),
(len(suffix), formats[fmt])]
return [(len(m.group()), formats[fmt])]
return [(len(text) - i, formats['unknown-normal'])]
def content(state, text, i, formats, user_data):
' Inside content blocks '
m = space_pat.match(text, i)
if m is not None:
return [(len(m.group()), None)]
cdo = cdo_pat.match(text, i)
if cdo is not None:
state.parse = IN_COMMENT_CONTENT
return [(len(cdo.group()), formats['comment'])]
if text[i] == '"':
state.parse = IN_DQS
return [(1, formats['string'])]
if text[i] == "'":
state.parse = IN_SQS
return [(1, formats['string'])]
if text[i] == '}':
state.blocks -= 1
state.parse = NORMAL if state.blocks < 1 else IN_CONTENT
return [(1, formats['bracket'])]
if text[i] == '{':
state.blocks += 1
return [(1, formats['bracket'])]
for token, fmt, name in content_tokens:
m = token.match(text, i)
if m is not None:
if name is URL_TOKEN:
h = 'link'
url = m.group()
prefix, main, suffix = url[:4], url[4:-1], url[-1]
if len(main) > 1 and main[0] in ('"', "'") and main[0] == main[-1]:
prefix += main[0]
suffix = main[-1] + suffix
main = main[1:-1]
h = 'bad_link' if verify_link(main, user_data.doc_name) is False else 'link'
return [(len(prefix), formats[fmt]), (len(main), formats[h]), (len(suffix), formats[fmt])]
return [(len(m.group()), formats[fmt])]
return [(len(text) - i, formats['unknown-normal'])]