我使用 Markdown 写博客已经有段时间了，但是一直以来有个小小的问题：对于代码块，markdown 生成的是一个<pre>标签里套一个<code>标签。缩进四个空格还好，用 Vim 的列编辑就行了（>操作不行，因为空行不会被缩进），可是删除这些<code>标签并加上相应的语言标识很烦。于是有了以下 Python 代码，使用的是 Python 版的 markdown，支持使用~~~~作为代码分隔符，如：
1 2 3 | ~~~~python|这是 Python 代码print('Hello Python!')~~~~ |
将会被翻译为
1 2 | <pre class="brush: python;" title="这是 Python 代码">print('Hello Python!')</pre> |
程序如下：
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 | #!/usr/bin/env python3# vim:fileencoding=utf-8import sysfrom itertools import takewhileimport markdownfrom lxml.html import fromstring, tostringdef parseAttr(s): a = s.split('|') if len(a) > 3: raise ValueError('Too many attributes') a = list(map(str.strip, a)) if len(a) == 3: a[2] = bool(a[2]) elif len(a) == 2: a.append(False) elif len(a) == 1: a.extend(['', False]) else: a = ['plain', '', False] if not a[0]: a[0] = 'plain' return adef analyseAttrs(text): '''Attributes are defined like this: ~~~~lang|title|collapse In place of ``collapse``, anything not empty is considered true. ''' incode = False lines = [] attrs = [] istilda = lambda ch: ch == '~' for l in text.split('\n'): if l.startswith('~~~~'): if not incode: incode = len(tuple(takewhile(istilda, l))) attr = parseAttr(l.lstrip('~')) attrs.append(attr) l = tildas = '~' * incode else: if l.find(tildas) == 0: incode = False lines.append(l) return '\n'.join(lines), attrsdef applyAttrs(html, attrs): doc = fromstring(html) for i, code in enumerate(doc.xpath('//pre/code')): pre = code.getparent() text = pre[0].text del pre[:] pre.text = text attr = attrs[i] c = 'brush: %s;' % attr[0] if attr[2]: c += ' collapse: true;' pre.set('class', c) if attr[1]: pre.set('title', attr[1]) return tostring(doc, encoding=str)[5:-6] + '\n'def main(): text = sys.stdin.read() text, attrs = analyseAttrs(text) out = markdown.markdown(text, ['fenced_code']) out = applyAttrs(out, attrs) sys.stdout.write(out)if __name__ == '__main__': main() |
