| 1 | #!/usr/bin/env python |
|---|
| 2 | # created my Massimo Di Pierro |
|---|
| 3 | # license MIT/BSD/GPL |
|---|
| 4 | from __future__ import print_function |
|---|
| 5 | import re |
|---|
| 6 | import cgi |
|---|
| 7 | import sys |
|---|
| 8 | import doctest |
|---|
| 9 | from optparse import OptionParser |
|---|
| 10 | |
|---|
| 11 | __all__ = ['render', 'markmin2latex'] |
|---|
| 12 | |
|---|
| 13 | META = 'META' |
|---|
| 14 | regex_newlines = re.compile('(\n\r)|(\r\n)') |
|---|
| 15 | regex_dd = re.compile('\$\$(?P<latex>.*?)\$\$') |
|---|
| 16 | regex_code = re.compile('(' + META + ')|(``(?P<t>.*?)``(:(?P<c>\w+))?)', re.S) |
|---|
| 17 | regex_title = re.compile('^#{1} (?P<t>[^\n]+)', re.M) |
|---|
| 18 | regex_maps = [ |
|---|
| 19 | (re.compile('[ \t\r]+\n'), '\n'), |
|---|
| 20 | (re.compile('\*\*(?P<t>[^\s\*]+( +[^\s\*]+)*)\*\*'), '{\\\\bf \g<t>}'), |
|---|
| 21 | (re.compile("''(?P<t>[^\s']+( +[^\s']+)*)''"), '{\\\it \g<t>}'), |
|---|
| 22 | (re.compile('^#{5,6}\s*(?P<t>[^\n]+)', re.M), '\n\n{\\\\bf \g<t>}\n'), |
|---|
| 23 | (re.compile('^#{4}\s*(?P<t>[^\n]+)', re.M), '\n\n\\\\goodbreak\\\subsubsection{\g<t>}\n'), |
|---|
| 24 | (re.compile('^#{3}\s*(?P<t>[^\n]+)', re.M), '\n\n\\\\goodbreak\\\subsection{\g<t>}\n'), |
|---|
| 25 | (re.compile('^#{2}\s*(?P<t>[^\n]+)', re.M), '\n\n\\\\goodbreak\\\section{\g<t>}\n'), |
|---|
| 26 | (re.compile('^#{1}\s*(?P<t>[^\n]+)', re.M), ''), |
|---|
| 27 | (re.compile('^\- +(?P<t>.*)', re.M), '\\\\begin{itemize}\n\\\item \g<t>\n\\\end{itemize}'), |
|---|
| 28 | (re.compile('^\+ +(?P<t>.*)', re.M), '\\\\begin{itemize}\n\\\item \g<t>\n\\\end{itemize}'), |
|---|
| 29 | (re.compile('\\\\end\{itemize\}\s+\\\\begin\{itemize\}'), '\n'), |
|---|
| 30 | (re.compile('\n\s+\n'), '\n\n')] |
|---|
| 31 | regex_table = re.compile('^\-{4,}\n(?P<t>.*?)\n\-{4,}(:(?P<c>\w+))?\n', re.M | re.S) |
|---|
| 32 | |
|---|
| 33 | regex_anchor = re.compile('\[\[(?P<t>\S+)\]\]') |
|---|
| 34 | regex_bibitem = re.compile('\-\s*\[\[(?P<t>\S+)\]\]') |
|---|
| 35 | regex_image_width = re.compile('\[\[(?P<t>[^\]]*?) +(?P<k>\S+) +(?P<p>left|right|center) +(?P<w>\d+px)\]\]') |
|---|
| 36 | regex_image = re.compile('\[\[(?P<t>[^\]]*?) +(?P<k>\S+) +(?P<p>left|right|center)\]\]') |
|---|
| 37 | # regex_video = re.compile('\[\[(?P<t>[^\]]*?) +(?P<k>\S+) +video\]\]') |
|---|
| 38 | # regex_audio = re.compile('\[\[(?P<t>[^\]]*?) +(?P<k>\S+) +audio\]\]') |
|---|
| 39 | regex_link = re.compile('\[\[(?P<t>[^\]]*?) +(?P<k>\S+)\]\]') |
|---|
| 40 | regex_auto = re.compile('(?<!["\w])(?P<k>\w+://[\w\.\-\?&%\:]+)', re.M) |
|---|
| 41 | regex_commas = re.compile('[ ]+(?P<t>[,;\.])') |
|---|
| 42 | regex_noindent = re.compile('\n\n(?P<t>[a-z])') |
|---|
| 43 | |
|---|
| 44 | |
|---|
| 45 | # regex_quote_left = re.compile('"(?=\w)') |
|---|
| 46 | # regex_quote_right = re.compile('(?=\w\.)"') |
|---|
| 47 | |
|---|
| 48 | def latex_escape(text, pound=True): |
|---|
| 49 | text = text.replace('\\', '{\\textbackslash}') |
|---|
| 50 | for c in '^_&$%{}': |
|---|
| 51 | text = text.replace(c, '\\' + c) |
|---|
| 52 | text = text.replace('\\{\\textbackslash\\}', '{\\textbackslash}') |
|---|
| 53 | if pound: text = text.replace('#', '\\#') |
|---|
| 54 | return text |
|---|
| 55 | |
|---|
| 56 | |
|---|
| 57 | def render(text, |
|---|
| 58 | extra={}, |
|---|
| 59 | allowed={}, |
|---|
| 60 | sep='p', |
|---|
| 61 | image_mapper=lambda x: x, |
|---|
| 62 | chapters=False): |
|---|
| 63 | ############################################################# |
|---|
| 64 | # replace all blocks marked with ``...``:class with META |
|---|
| 65 | # store them into segments they will be treated as code |
|---|
| 66 | ############################################################# |
|---|
| 67 | text = str(text or '') |
|---|
| 68 | segments, i = [], 0 |
|---|
| 69 | text = regex_dd.sub('``\g<latex>``:latex ', text) |
|---|
| 70 | text = regex_newlines.sub('\n', text) |
|---|
| 71 | while True: |
|---|
| 72 | item = regex_code.search(text, i) |
|---|
| 73 | if not item: |
|---|
| 74 | break |
|---|
| 75 | if item.group() == META: |
|---|
| 76 | segments.append((None, None)) |
|---|
| 77 | text = text[:item.start()] + META + text[item.end():] |
|---|
| 78 | else: |
|---|
| 79 | c = item.group('c') or '' |
|---|
| 80 | if 'code' in allowed and c not in allowed['code']: |
|---|
| 81 | c = '' |
|---|
| 82 | code = item.group('t').replace('!`!', '`') |
|---|
| 83 | segments.append((code, c)) |
|---|
| 84 | text = text[:item.start()] + META + text[item.end():] |
|---|
| 85 | i = item.start() + 3 |
|---|
| 86 | |
|---|
| 87 | ############################################################# |
|---|
| 88 | # do h1,h2,h3,h4,h5,h6,b,i,ol,ul and normalize spaces |
|---|
| 89 | ############################################################# |
|---|
| 90 | |
|---|
| 91 | title = regex_title.search(text) |
|---|
| 92 | if not title: |
|---|
| 93 | title = 'Title' |
|---|
| 94 | else: |
|---|
| 95 | title = title.group('t') |
|---|
| 96 | |
|---|
| 97 | text = latex_escape(text, pound=False) |
|---|
| 98 | |
|---|
| 99 | texts = text.split('## References', 1) |
|---|
| 100 | text = regex_anchor.sub('\\\label{\g<t>}', texts[0]) |
|---|
| 101 | if len(texts) == 2: |
|---|
| 102 | text += '\n\\begin{thebibliography}{999}\n' |
|---|
| 103 | text += regex_bibitem.sub('\n\\\\bibitem{\g<t>}', texts[1]) |
|---|
| 104 | text += '\n\\end{thebibliography}\n' |
|---|
| 105 | |
|---|
| 106 | text = '\n'.join(t.strip() for t in text.split('\n')) |
|---|
| 107 | for regex, sub in regex_maps: |
|---|
| 108 | text = regex.sub(sub, text) |
|---|
| 109 | text = text.replace('#', '\\#') |
|---|
| 110 | text = text.replace('`', "'") |
|---|
| 111 | |
|---|
| 112 | ############################################################# |
|---|
| 113 | # process tables and blockquotes |
|---|
| 114 | ############################################################# |
|---|
| 115 | while True: |
|---|
| 116 | item = regex_table.search(text) |
|---|
| 117 | if not item: |
|---|
| 118 | break |
|---|
| 119 | c = item.group('c') or '' |
|---|
| 120 | if 'table' in allowed and c not in allowed['table']: |
|---|
| 121 | c = '' |
|---|
| 122 | content = item.group('t') |
|---|
| 123 | if ' | ' in content: |
|---|
| 124 | rows = content.replace('\n', '\\\\\n').replace(' | ', ' & ') |
|---|
| 125 | row0, row2 = rows.split('\\\\\n', 1) |
|---|
| 126 | cols = row0.count(' & ') + 1 |
|---|
| 127 | cal = '{' + ''.join('l' for j in range(cols)) + '}' |
|---|
| 128 | tabular = '\\begin{center}\n{\\begin{tabular}' + cal + '\\hline\n' + row0 + '\\\\ \\hline\n' + row2 + ' \\\\ \\hline\n\\end{tabular}}\n\\end{center}' |
|---|
| 129 | if row2.count('\n') > 20: |
|---|
| 130 | tabular = '\\newpage\n' + tabular |
|---|
| 131 | text = text[:item.start()] + tabular + text[item.end():] |
|---|
| 132 | else: |
|---|
| 133 | text = text[:item.start()] + '\\begin{quote}' + content + '\\end{quote}' + text[item.end():] |
|---|
| 134 | |
|---|
| 135 | ############################################################# |
|---|
| 136 | # deal with images, videos, audios and links |
|---|
| 137 | ############################################################# |
|---|
| 138 | |
|---|
| 139 | def sub(x): |
|---|
| 140 | f = image_mapper(x.group('k')) |
|---|
| 141 | if not f: |
|---|
| 142 | return None |
|---|
| 143 | return '\n\\begin{center}\\includegraphics[width=8cm]{%s}\\end{center}\n' % f |
|---|
| 144 | |
|---|
| 145 | text = regex_image_width.sub(sub, text) |
|---|
| 146 | text = regex_image.sub(sub, text) |
|---|
| 147 | |
|---|
| 148 | text = regex_link.sub('{\\\\footnotesize\\\href{\g<k>}{\g<t>}}', text) |
|---|
| 149 | text = regex_commas.sub('\g<t>', text) |
|---|
| 150 | text = regex_noindent.sub('\n\\\\noindent \g<t>', text) |
|---|
| 151 | |
|---|
| 152 | # ## fix paths in images |
|---|
| 153 | regex = re.compile('\\\\_\w*\.(eps|png|jpg|gif)') |
|---|
| 154 | while True: |
|---|
| 155 | match = regex.search(text) |
|---|
| 156 | if not match: |
|---|
| 157 | break |
|---|
| 158 | text = text[:match.start()] + text[match.start() + 1:] |
|---|
| 159 | # text = regex_quote_left.sub('``',text) |
|---|
| 160 | # text = regex_quote_right.sub("''",text) |
|---|
| 161 | |
|---|
| 162 | if chapters: |
|---|
| 163 | text = text.replace(r'\section*{', r'\chapter*{') |
|---|
| 164 | text = text.replace(r'\section{', r'\chapter{') |
|---|
| 165 | text = text.replace(r'subsection{', r'section{') |
|---|
| 166 | |
|---|
| 167 | ############################################################# |
|---|
| 168 | # process all code text |
|---|
| 169 | ############################################################# |
|---|
| 170 | parts = text.split(META) |
|---|
| 171 | text = parts[0] |
|---|
| 172 | authors = [] |
|---|
| 173 | for i, (code, b) in enumerate(segments): |
|---|
| 174 | if code is None: |
|---|
| 175 | html = META |
|---|
| 176 | else: |
|---|
| 177 | if b == 'hidden': |
|---|
| 178 | html = '' |
|---|
| 179 | elif b == 'author': |
|---|
| 180 | author = latex_escape(code.strip()) |
|---|
| 181 | authors.append(author) |
|---|
| 182 | html = '' |
|---|
| 183 | elif b == 'inxx': |
|---|
| 184 | html = '\inxx{%s}' % latex_escape(code) |
|---|
| 185 | elif b == 'cite': |
|---|
| 186 | html = '~\cite{%s}' % latex_escape(code.strip()) |
|---|
| 187 | elif b == 'ref': |
|---|
| 188 | html = '~\ref{%s}' % latex_escape(code.strip()) |
|---|
| 189 | elif b == 'latex': |
|---|
| 190 | if '\n' in code: |
|---|
| 191 | html = '\n\\begin{equation}\n%s\n\\end{equation}\n' % code.strip() |
|---|
| 192 | else: |
|---|
| 193 | html = '$%s$' % code.strip() |
|---|
| 194 | elif b == 'latex_eqnarray': |
|---|
| 195 | code = code.strip() |
|---|
| 196 | code = '\\\\'.join(x.replace('=', '&=&', 1) for x in code.split('\\\\')) |
|---|
| 197 | html = '\n\\begin{eqnarray}\n%s\n\\end{eqnarray}\n' % code |
|---|
| 198 | elif b.startswith('latex_'): |
|---|
| 199 | key = b[6:] |
|---|
| 200 | html = '\\begin{%s}%s\\end{%s}' % (key, code, key) |
|---|
| 201 | elif b in extra: |
|---|
| 202 | if code[:1] == '\n': |
|---|
| 203 | code = code[1:] |
|---|
| 204 | if code[-1:] == '\n': |
|---|
| 205 | code = code[:-1] |
|---|
| 206 | html = extra[b](code) |
|---|
| 207 | elif code[:1] == '\n' or code[:-1] == '\n': |
|---|
| 208 | if code[:1] == '\n': |
|---|
| 209 | code = code[1:] |
|---|
| 210 | if code[-1:] == '\n': |
|---|
| 211 | code = code[:-1] |
|---|
| 212 | if code.startswith('<') or code.startswith('{{') or code.startswith('http'): |
|---|
| 213 | html = '\\begin{lstlisting}[keywords={}]\n%s\n\\end{lstlisting}' % code |
|---|
| 214 | else: |
|---|
| 215 | html = '\\begin{lstlisting}\n%s\n\\end{lstlisting}' % code |
|---|
| 216 | else: |
|---|
| 217 | if code[:1] == '\n': |
|---|
| 218 | code = code[1:] |
|---|
| 219 | if code[-1:] == '\n': |
|---|
| 220 | code = code[:-1] |
|---|
| 221 | html = '{\\ft %s}' % latex_escape(code) |
|---|
| 222 | try: |
|---|
| 223 | text = text + html + parts[i + 1] |
|---|
| 224 | except: |
|---|
| 225 | text = text + '... WIKI PROCESSING ERROR ...' |
|---|
| 226 | break |
|---|
| 227 | text = text.replace(' ~\\cite', '~\\cite') |
|---|
| 228 | return text, title, authors |
|---|
| 229 | |
|---|
| 230 | |
|---|
| 231 | WRAPPER = """ |
|---|
| 232 | \\documentclass[12pt]{article} |
|---|
| 233 | \\usepackage{hyperref} |
|---|
| 234 | \\usepackage{listings} |
|---|
| 235 | \\usepackage{upquote} |
|---|
| 236 | \\usepackage{color} |
|---|
| 237 | \\usepackage{graphicx} |
|---|
| 238 | \\usepackage{grffile} |
|---|
| 239 | \\usepackage[utf8x]{inputenc} |
|---|
| 240 | \\usepackage{textgreek} |
|---|
| 241 | \\definecolor{lg}{rgb}{0.9,0.9,0.9} |
|---|
| 242 | \\definecolor{dg}{rgb}{0.3,0.3,0.3} |
|---|
| 243 | \\def\\ft{\\small\\tt} |
|---|
| 244 | \\lstset{ |
|---|
| 245 | basicstyle=\\footnotesize, |
|---|
| 246 | breaklines=true, basicstyle=\\ttfamily\\color{black}\\footnotesize, |
|---|
| 247 | keywordstyle=\\bf\\ttfamily, |
|---|
| 248 | commentstyle=\\it\\ttfamily, |
|---|
| 249 | stringstyle=\\color{dg}\\it\\ttfamily, |
|---|
| 250 | numbers=left, numberstyle=\\color{dg}\\tiny, stepnumber=1, numbersep=5pt, |
|---|
| 251 | backgroundcolor=\\color{lg}, tabsize=4, showspaces=false, |
|---|
| 252 | showstringspaces=false |
|---|
| 253 | } |
|---|
| 254 | \\title{%(title)s} |
|---|
| 255 | \\author{%(author)s} |
|---|
| 256 | \\begin{document} |
|---|
| 257 | \\maketitle |
|---|
| 258 | \\tableofcontents |
|---|
| 259 | \\newpage |
|---|
| 260 | %(body)s |
|---|
| 261 | \\end{document} |
|---|
| 262 | """ |
|---|
| 263 | |
|---|
| 264 | |
|---|
| 265 | def markmin2latex(data, image_mapper=lambda x: x, extra={}, |
|---|
| 266 | wrapper=WRAPPER): |
|---|
| 267 | body, title, authors = render(data, extra=extra, image_mapper=image_mapper) |
|---|
| 268 | author = '\n\\and\n'.join(a.replace('\n', '\\\\\n\\footnotesize ') for a in authors) |
|---|
| 269 | return wrapper % dict(title=title, author=author, body=body) |
|---|
| 270 | |
|---|
| 271 | |
|---|
| 272 | if __name__ == '__main__': |
|---|
| 273 | parser = OptionParser() |
|---|
| 274 | parser.add_option("-i", "--info", dest="info", |
|---|
| 275 | help="markmin help") |
|---|
| 276 | parser.add_option("-t", "--test", dest="test", action="store_true", |
|---|
| 277 | default=False) |
|---|
| 278 | parser.add_option("-n", "--no_wrapper", dest="no_wrapper", |
|---|
| 279 | action="store_true", default=False) |
|---|
| 280 | parser.add_option("-c", "--chapters", dest="chapters", action="store_true", |
|---|
| 281 | default=False, help="switch section for chapter") |
|---|
| 282 | parser.add_option("-w", "--wrapper", dest="wrapper", default=False, |
|---|
| 283 | help="latex file containing header and footer") |
|---|
| 284 | |
|---|
| 285 | (options, args) = parser.parse_args() |
|---|
| 286 | if options.info: |
|---|
| 287 | import markmin2html |
|---|
| 288 | |
|---|
| 289 | markmin2latex(markmin2html.__doc__) |
|---|
| 290 | elif options.test: |
|---|
| 291 | doctest.testmod() |
|---|
| 292 | else: |
|---|
| 293 | if options.wrapper: |
|---|
| 294 | fwrapper = open(options.wrapper, 'rb') |
|---|
| 295 | try: |
|---|
| 296 | wrapper = fwrapper.read() |
|---|
| 297 | finally: |
|---|
| 298 | fwrapper.close() |
|---|
| 299 | elif options.no_wrapper: |
|---|
| 300 | wrapper = '%(body)s' |
|---|
| 301 | else: |
|---|
| 302 | wrapper = WRAPPER |
|---|
| 303 | for f in args: |
|---|
| 304 | fargs = open(f, 'r') |
|---|
| 305 | content_data = [] |
|---|
| 306 | try: |
|---|
| 307 | content_data.append(fargs.read()) |
|---|
| 308 | finally: |
|---|
| 309 | fargs.close() |
|---|
| 310 | content = '\n'.join(content_data) |
|---|
| 311 | output = markmin2latex(content, |
|---|
| 312 | wrapper=wrapper, |
|---|
| 313 | chapters=options.chapters) |
|---|
| 314 | print(output) |
|---|
