def escapestyle(self, m):
Lexer.tokenize(self, m.group('l_data2'))
token = Token(type='text', value=m.group('inner'))
self.ts.append(token)
Lexer.tokenize(self, m.group('r_data2'))
def images(self, m):
Lexer.tokenize(self, m.group('l_data3'))
v = {'alt': m.group('alt1'),
'link': m.group('i_link1'),
'all_tag': m.group('all_tag1')}
token = Token(type='image', value=v)
self.ts.append(token)
Lexer.tokenize(self, m.group('r_data3'))
def links(self, m):
Lexer.tokenize(self, m.group('l_data2'))
v = {'text': m.group('l_text'),
'link': m.group('l_link'),
'all_tag': m.group('all_tag3')}
token = Token(type='link', value=v)
self.ts.append(token)
Lexer.tokenize(self, m.group('r_data2'))
def link_images(self, m):
Lexer.tokenize(self, m.group('l_data4'))
v = {'alt': m.group('alt2'),
'img_link': m.group('i_link2'),
'page_link': m.group('page_link'),
'all_tag': m.group('all_tag2')}
token = Token(type='imagelink', value=v)
self.ts.append(token)
Lexer.tokenize(self, m.group('r_data4'))
def __init__(self):
img_reg = r'(?P<all_tag%s> !(?P<i_link%s>[^\s]+)\s*\((?P<alt%s>.*)\)! )'
tokens = [
('text_style', r'(?P<l_data1>.*?) %(?P<format>\(.*?\)|{.*?})\ (?P<text>%*.*?%*) % (?P<r_data1>.*?)'),
('links', r'(?P<l_data2>.*?) (?P<all_tag3> "(?P<l_text>[^"]+?)":\((?P<l_link>.+?)\) ) (?P<r_data2>.*?)'),
('link_images', r'(?P<l_data4>.*?) %s:\((?P<page_link>.+?)\) (?P<r_data4>.*?)' % img_reg % (2, 2, 2)),
('images', r'(?P<l_data3>.*?) %s (?P<r_data3>.*?)' % img_reg % (1, 1, 1)),
('line_break', r'\n'),
('data', r'.+')
]
Lexer.__init__(self, tokens)
def __init__(self):
tokens = [
('header', r'h([1-6])(\.|!)\ ?'),
('list_item', r'\*\s* (.+)'),
('line_break', r'\n'),
('escapestyle', r'(?P<l_data2>.*?) (?P<inner> \[escapestyle\] ([^$]*?) \[/escapestyle\] ) (?P<r_data2>.*?)'),
('escape', r'\[escape\] ([^$]*?) \[/escape\]'),
('code', r'\[code\] ((.|\s)*?) \[/code\]'),
('plugin', r'(?P<l_data1>.*?) (?P<all_tag> \[(?P<p_name2> ((\[.+?\]) | [^\]])+? )\]) (?P<r_data1>.*?)'),
('text', r'.+')
]
Lexer.__init__(self, tokens)
self.is_plugin = re.compile('\w+([,=]|$)')
def plugin(self, m):
#We support escape by [!
name = m.group('p_name2')
all_tag = m.group('all_tag')
if name.find('!') == 0:
token = Token(type='text', value=all_tag.replace('[!', '[', 1))
elif name.find('/') == 0:
token = Token(type='plugin_end', value='[%s]' % name)
elif self.is_plugin.match(name):
v = {
'inner_tag': name,
'all_tag': all_tag
}
token = Token(type='plugin_start', value=v)
else:
#It's not a plugin!
token = None
Lexer.tokenize(self, m.group('l_data1'))
if token:
self.ts.append(token)
else:
self.ts.append(Token(type='text', value='['))
Lexer.tokenize(self, name)
self.ts.append(Token(type='text', value=']'))
Lexer.tokenize(self, m.group('r_data1'))
def text_style(self, m):
Lexer.tokenize(self, m.group('l_data1'))
format = m.group('format')
text = m.group('text')
html_style = re.match('\(([bius])\s*\)', format)
span_class = re.match('\((\w+)\)', format)
span_style = re.match('{(\w+.+)}', format)
token = None
tag_or_cls = None
if html_style:
tag_or_cls = html_style.group(1)
token = Token(type='html_tag_start', value=tag_or_cls)
elif span_class:
tag_or_cls = span_class.group(1)
token = Token(type='span_class_start', value=tag_or_cls)
elif span_style:
span_inner = span_style.group(1)
try:
spl = span_inner.split(",")
style = []
for item in spl:
k, v = item.split(":")
v = v.strip()
style.append("%s: %s" % (k, v))
style = ';'.join(style)
token = Token(type='span_style_start', value=style)
except:
token = Token(type='text', value=span_style.group(0))
else:
token = Token(type='text', value=format)
self.ts.append(token)
#Recursively handle the inner text
#since we need to support %(b) %(i) Hej%%
Lexer.tokenize(self, text)
if html_style:
token = Token(type='html_tag_end', value=tag_or_cls)
else:
token = Token(type='span_end')
self.ts.append(token)
Lexer.tokenize(self, m.group('r_data1'))
def escape(self, m):
print 'her!!'
self.ts.append(Token(type='escape_start'))
Lexer.tokenize(self, m.group(1))
self.ts.append(Token(type='escape_end'))
def list_item(self, m):
self.ts.append(Token(type='list_item_start'))
Lexer.tokenize(self, m.group(1))
self.ts.append(Token(type='list_item_end'))
def tokenize(self, text):
self.ts = []
Lexer.tokenize(self, text)
return self.ts