diff --git a/gluon/contrib/markmin/markmin2html.py b/gluon/contrib/markmin/markmin2html.py index af27404e..09f6de08 100755 --- a/gluon/contrib/markmin/markmin2html.py +++ b/gluon/contrib/markmin/markmin2html.py @@ -5,12 +5,19 @@ # license MIT/BSD/GPL from __future__ import print_function import re +import sys import urllib -from gluon._compat import maketrans, urllib_quote, unicodeT, to_bytes, to_native, xrange -from gluon.utils import local_html_escape as escape -from ast import parse as ast_parse import ast +PY2 = sys.version_info[0] == 2 + +if PY2: + from urllib import quote as urllib_quote + from string import maketrans +else: + from urllib.parse import quote as urllib_quote + maketrans = str.maketrans + """ TODO: next version should use MathJax @@ -564,6 +571,29 @@ ttab_in = maketrans("'`:*~\\[]{}@$+-.#\n", '\x0b\x0c\x0e\x0f\x10\x11\x12\x13\x14 ttab_out = maketrans('\x0b\x0c\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x05', "'`:*~\\[]{}@$+-.#\n") regex_quote = re.compile('(?P\w+?)\s*\=\s*') +def local_html_escape(data, quote=False): + """ + Works with bytes. + Replace special characters "&", "<" and ">" to HTML-safe sequences. + If the optional flag quote is true (the default), the quotation mark + characters, both double quote (") and single quote (') characters are also + translated. + """ + if PY2: + import cgi + data = cgi.escape(data, quote) + return data.replace("'", "'") if quote else data + else: + import html + if isinstance(data, str): + return html.escape(data, quote=quote) + data = data.replace(b"&", b"&") # Must be done first! + data = data.replace(b"<", b"<") + data = data.replace(b">", b">") + if quote: + data = data.replace(b'"', b""") + data = data.replace(b'\'', b"'") + return data def make_dict(b): return '{%s}' % regex_quote.sub("'\g':", b) @@ -579,7 +609,7 @@ def safe_eval(node_or_string, env): _safe_names = {'None': None, 'True': True, 'False': False} _safe_names.update(env) if isinstance(node_or_string, basestring): - node_or_string = ast_parse(node_or_string, mode='eval') + node_or_string = ast.parse(node_or_string, mode='eval') if isinstance(node_or_string, ast.Expression): node_or_string = node_or_string.body @@ -599,14 +629,14 @@ def safe_eval(node_or_string, env): if node.id in _safe_names: return _safe_names[node.id] elif isinstance(node, ast.BinOp) and \ - isinstance(node.op, (Add, Sub)) and \ - isinstance(node.right, Num) and \ + isinstance(node.op, (ast.Add, ast.Sub)) and \ + isinstance(node.right, ast.Num) and \ isinstance(node.right.n, complex) and \ - isinstance(node.left, Num) and \ + isinstance(node.left, ast.Num) and \ isinstance(node.left.n, (int, long, float)): left = node.left.n right = node.right.n - if isinstance(node.op, Add): + if isinstance(node.op, ast.Add): return left + right else: return left - right @@ -946,7 +976,8 @@ def render(text, if protolinks == "default": protolinks = protolinks_simple pp = '\n' if pretty_print else '' - text = to_native(text) + text = text if text is None or isinstance(text, str) else text.decode('utf8', 'strict') + if not (isinstance(text, str)): text = str(text or '') text = regex_backslash.sub(lambda m: m.group(1).translate(ttab_in), text) @@ -994,7 +1025,7 @@ def render(text, return LINK text = regex_link.sub(mark_link, text) - text = escape(text) + text = local_html_escape(text) if protolinks: text = regex_proto.sub(lambda m: protolinks(*m.group('p', 'k')), text) @@ -1035,7 +1066,7 @@ def render(text, if pend and mtag == '.': # paragraph in a list: out.append(etags.pop()) ltags.pop() - for i in xrange(lent - lev): + for i in range(lent - lev): out.append('<' + tag + '>' + pp) etags.append('' + pp) lev += 1 @@ -1044,7 +1075,7 @@ def render(text, elif lent == lev: if tlev[-1] != tag: # type of list is changed (ul<=>ol): - for i in xrange(ltags.count(lent)): + for i in range(ltags.count(lent)): ltags.pop() out.append(etags.pop()) tlev[-1] = tag @@ -1209,7 +1240,7 @@ def render(text, s = '%s%s' \ % (t_cls, t_id, - '\n'.join(strings[bq_begin:lineno]), pp) + render('\n'.join(strings[bq_begin:lineno])), pp) mtag = 'q' else: s = '
' @@ -1322,10 +1353,10 @@ def render(text, t, a, k, p, w = m.group('t', 'a', 'k', 'p', 'w') if not k: return m.group(0) - k = escape(k) + k = local_html_escape(k) t = t or '' style = 'width:%s' % w if w else '' - title = ' title="%s"' % escape(a).replace(META, DISABLED_META) if a else '' + title = ' title="%s"' % local_html_escape(a).replace(META, DISABLED_META) if a else '' p_begin = p_end = '' if p == 'center': p_begin = '

' @@ -1349,7 +1380,7 @@ def render(text, autolinks, protolinks, class_prefix, id_prefix, pretty_print) return '<%(p)s controls="controls"%(title)s%(style)s>%(t)s' \ % dict(p=p, title=title, style=style, k=k, t=t) - alt = ' alt="%s"' % escape(t).replace(META, DISABLED_META) if t else '' + alt = ' alt="%s"' % local_html_escape(t).replace(META, DISABLED_META) if t else '' return '%(begin)s%(end)s' \ % dict(begin=p_begin, k=k, alt=alt, title=title, style=style, end=p_end) @@ -1358,12 +1389,12 @@ def render(text, if not k and not t: return m.group(0) t = t or '' - a = escape(a) if a else '' + a = local_html_escape(a) if a else '' if k: if '#' in k and ':' not in k.split('#')[0]: # wikipage, not external url k = k.replace('#', '#' + id_prefix) - k = escape(k) + k = local_html_escape(k) title = ' title="%s"' % a.replace(META, DISABLED_META) if a else '' target = ' target="_blank"' if p == 'popup' else '' t = render(t, {}, {}, 'br', URL, environment, latex, None, @@ -1373,7 +1404,7 @@ def render(text, if t == 'NEWLINE' and not a: return '
' + pp return '%s' % ( - escape(id_prefix + t), + local_html_escape(id_prefix + t), render(a, {}, {}, 'br', URL, environment, latex, autolinks, protolinks, class_prefix, @@ -1399,7 +1430,7 @@ def render(text, def expand_meta(m): code, b, p, s = segments.pop(0) if code is None or m.group() == DISABLED_META: - return escape(s) + return local_html_escape(s) if b in extra: if code[:1] == '\n': code = code[1:] @@ -1411,7 +1442,7 @@ def render(text, return str(extra[b](code)) elif b == 'cite': return '[' + ','.join('%s' % - (id_prefix + d, b, d) for d in escape(code).split(',')) + ']' + (id_prefix + d, b, d) for d in local_html_escape(code).split(',')) + ']' elif b == 'latex': return LATEX % urllib_quote(code) elif b in html_colors: @@ -1426,12 +1457,12 @@ def render(text, % (fg, bg, render(code, {}, {}, 'br', URL, environment, latex, autolinks, protolinks, class_prefix, id_prefix, pretty_print)) cls = ' class="%s%s"' % (class_prefix, b) if b and b != 'id' else '' - id = ' id="%s%s"' % (id_prefix, escape(p)) if p else '' + id = ' id="%s%s"' % (id_prefix, local_html_escape(p)) if p else '' beg = (code[:1] == '\n') end = [None, -1][code[-1:] == '\n'] if beg and end: - return '

%s
%s' % (cls, id, escape(code[1:-1]), pp) - return '%s' % (cls, id, escape(code[beg:end])) + return '
%s
%s' % (cls, id, local_html_escape(code[1:-1]), pp) + return '%s' % (cls, id, local_html_escape(code[beg:end])) text = regex_expand_meta.sub(expand_meta, text)