| 1 | #!/usr/bin/env python |
|---|
| 2 | # -*- coding: utf-8 -*- |
|---|
| 3 | # created by Massimo Di Pierro |
|---|
| 4 | # recreated by Vladyslav Kozlovskyy |
|---|
| 5 | # license MIT/BSD/GPL |
|---|
| 6 | from __future__ import print_function |
|---|
| 7 | import re |
|---|
| 8 | import sys |
|---|
| 9 | import urllib |
|---|
| 10 | import ast |
|---|
| 11 | |
|---|
| 12 | PY2 = sys.version_info[0] == 2 |
|---|
| 13 | |
|---|
| 14 | if PY2: |
|---|
| 15 | from urllib import quote as urllib_quote |
|---|
| 16 | from string import maketrans |
|---|
| 17 | else: |
|---|
| 18 | from urllib.parse import quote as urllib_quote |
|---|
| 19 | maketrans = str.maketrans |
|---|
| 20 | |
|---|
| 21 | |
|---|
| 22 | """ |
|---|
| 23 | TODO: next version should use MathJax |
|---|
| 24 | |
|---|
| 25 | <script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"> |
|---|
| 26 | MathJax.Hub.Config({ |
|---|
| 27 | extensions: ["tex2jax.js","TeX/AMSmath.js","TeX/AMSsymbols.js"], |
|---|
| 28 | jax: ["input/TeX", "output/HTML-CSS"], |
|---|
| 29 | tex2jax: { |
|---|
| 30 | inlineMath: [ ['$','$'], ["\\(","\\)"] ], |
|---|
| 31 | displayMath: [ ['$$','$$'], ["\\[","\\]"] ], |
|---|
| 32 | }, |
|---|
| 33 | "HTML-CSS": { availableFonts: ["TeX"] } |
|---|
| 34 | }); |
|---|
| 35 | </script> |
|---|
| 36 | """ |
|---|
| 37 | |
|---|
| 38 | __all__ = ['render', 'markmin2html', 'markmin_escape'] |
|---|
| 39 | |
|---|
| 40 | __doc__ = """ |
|---|
| 41 | # Markmin markup language |
|---|
| 42 | |
|---|
| 43 | ## About |
|---|
| 44 | |
|---|
| 45 | This is a new markup language that we call markmin designed to produce high quality scientific papers and books and also put them online. We provide serializers for html, latex and pdf. It is implemented in the ``markmin2html`` function in the ``markmin2html.py``. |
|---|
| 46 | |
|---|
| 47 | Example of usage: |
|---|
| 48 | |
|---|
| 49 | `` |
|---|
| 50 | m = "Hello **world** [[link http://web2py.com]]" |
|---|
| 51 | from markmin2html import markmin2html |
|---|
| 52 | print(markmin2html(m)) |
|---|
| 53 | from markmin2latex import markmin2latex |
|---|
| 54 | print(markmin2latex(m)) |
|---|
| 55 | from markmin2pdf import markmin2pdf # requires pdflatex |
|---|
| 56 | print(markmin2pdf(m)) |
|---|
| 57 | `` |
|---|
| 58 | ==================== |
|---|
| 59 | # This is a test block |
|---|
| 60 | with new features: |
|---|
| 61 | This is a blockquote with |
|---|
| 62 | a list with tables in it: |
|---|
| 63 | ----------- |
|---|
| 64 | This is a paragraph before list. |
|---|
| 65 | You can continue paragraph on the |
|---|
| 66 | next lines. |
|---|
| 67 | |
|---|
| 68 | This is an ordered list with tables: |
|---|
| 69 | + Item 1 |
|---|
| 70 | + Item 2 |
|---|
| 71 | + -------- |
|---|
| 72 | aa|bb|cc |
|---|
| 73 | 11|22|33 |
|---|
| 74 | --------:tableclass1[tableid1] |
|---|
| 75 | + Item 4 |
|---|
| 76 | ----------- |
|---|
| 77 | T1| T2| t3 |
|---|
| 78 | =========== |
|---|
| 79 | aaa|bbb|ccc |
|---|
| 80 | ddd|fff|ggg |
|---|
| 81 | 123|0 |5.0 |
|---|
| 82 | -----------:tableclass1 |
|---|
| 83 | -----------:blockquoteclass[blockquoteid] |
|---|
| 84 | |
|---|
| 85 | This this a new paragraph |
|---|
| 86 | with a followed table. |
|---|
| 87 | Table has header, footer, sections, |
|---|
| 88 | odd and even rows: |
|---|
| 89 | ------------------------------- |
|---|
| 90 | **Title 1**|**Title 2**|**Title 3** |
|---|
| 91 | ============================== |
|---|
| 92 | data 1 | data 2 | 2.00 |
|---|
| 93 | data 3 |data4(long)| 23.00 |
|---|
| 94 | |data 5 | 33.50 |
|---|
| 95 | ============================== |
|---|
| 96 | New section|New data | 5.00 |
|---|
| 97 | data 1 |data2(long)|100.45 |
|---|
| 98 | |data 3 | 12.50 |
|---|
| 99 | data 4 | data 5 | .33 |
|---|
| 100 | data 6 |data7(long)| 8.01 |
|---|
| 101 | |data 8 | 514 |
|---|
| 102 | ============================== |
|---|
| 103 | Total: | 9 items |698,79 |
|---|
| 104 | ------------------------------:tableclass1[tableid2] |
|---|
| 105 | |
|---|
| 106 | ## Multilevel |
|---|
| 107 | lists |
|---|
| 108 | |
|---|
| 109 | Now lists can be multilevel: |
|---|
| 110 | |
|---|
| 111 | + Ordered item 1 on level 1. |
|---|
| 112 | You can continue item text on |
|---|
| 113 | next strings |
|---|
| 114 | |
|---|
| 115 | . paragraph in an item |
|---|
| 116 | |
|---|
| 117 | ++. Ordered item 1 of sublevel 2 with |
|---|
| 118 | a paragraph (paragraph can start |
|---|
| 119 | with point after plus or minus |
|---|
| 120 | characters, e.g. **++.** or **--.**) |
|---|
| 121 | |
|---|
| 122 | ++. This is another item. But with 3 paragraphs, |
|---|
| 123 | blockquote and sublists: |
|---|
| 124 | |
|---|
| 125 | .. This is the second paragraph in the item. You |
|---|
| 126 | can add paragraphs to an item, using point |
|---|
| 127 | notation, where first characters in the string |
|---|
| 128 | are sequence of points with space between |
|---|
| 129 | them and another string. For example, this |
|---|
| 130 | paragraph (in sublevel 2) starts with two points: |
|---|
| 131 | ``.. This is the second paragraph...`` |
|---|
| 132 | |
|---|
| 133 | .. ---------- |
|---|
| 134 | ### this is a blockquote in a list |
|---|
| 135 | |
|---|
| 136 | You can use blockquote with headers, paragraphs, |
|---|
| 137 | tables and lists in it: |
|---|
| 138 | |
|---|
| 139 | Tables can have or have not header and footer. |
|---|
| 140 | This table is defined without any header |
|---|
| 141 | and footer in it: |
|---|
| 142 | --------------------- |
|---|
| 143 | red |fox | 0 |
|---|
| 144 | blue |dolphin | 1000 |
|---|
| 145 | green|leaf | 10000 |
|---|
| 146 | --------------------- |
|---|
| 147 | ---------- |
|---|
| 148 | |
|---|
| 149 | .. This is yet another paragraph in the item. |
|---|
| 150 | |
|---|
| 151 | --- This is an item of unordered list **(sublevel 3)** |
|---|
| 152 | --- This is the second item of the unordered list ''(sublevel 3)'' |
|---|
| 153 | |
|---|
| 154 | ++++++ This is a single item of ordered list in sublevel 6 |
|---|
| 155 | .... and this is a paragraph in sublevel 4 |
|---|
| 156 | ---. This is a new item with paragraph in sublevel 3. |
|---|
| 157 | ++++ Start ordered list in sublevel 4 with code block: `` |
|---|
| 158 | line 1 |
|---|
| 159 | line 2 |
|---|
| 160 | line 3 |
|---|
| 161 | `` |
|---|
| 162 | ++++. Yet another item with code block (we need to indent \`\` to add code block as part of item): |
|---|
| 163 | `` |
|---|
| 164 | line 1 |
|---|
| 165 | line 2 |
|---|
| 166 | line 3 |
|---|
| 167 | `` |
|---|
| 168 | This item finishes with this paragraph. |
|---|
| 169 | |
|---|
| 170 | ... Item in sublevel 3 can be continued with paragraphs. |
|---|
| 171 | |
|---|
| 172 | ... `` |
|---|
| 173 | this is another |
|---|
| 174 | code block |
|---|
| 175 | in the |
|---|
| 176 | sublevel 3 item |
|---|
| 177 | `` |
|---|
| 178 | |
|---|
| 179 | +++ The last item in sublevel 3 |
|---|
| 180 | .. This is a continuous paragraph for item 2 in sublevel 2. |
|---|
| 181 | You can use such structure to create difficult structured |
|---|
| 182 | documents. |
|---|
| 183 | |
|---|
| 184 | ++ item 3 in sublevel 2 |
|---|
| 185 | -- item 1 in sublevel 2 (new unordered list) |
|---|
| 186 | -- item 2 in sublevel 2 |
|---|
| 187 | -- item 3 in sublevel 2 |
|---|
| 188 | |
|---|
| 189 | ++ item 1 in sublevel 2 (new ordered list) |
|---|
| 190 | ++ item 2 in sublevel 2 |
|---|
| 191 | ++ item 3 in sublevle 2 |
|---|
| 192 | |
|---|
| 193 | + item 2 in level 1 |
|---|
| 194 | + item 3 in level 1 |
|---|
| 195 | - new unordered list (item 1 in level 1) |
|---|
| 196 | - level 2 in level 1 |
|---|
| 197 | |
|---|
| 198 | - level 3 in level 1 |
|---|
| 199 | - level 4 in level 1 |
|---|
| 200 | ## This is the last section of the test |
|---|
| 201 | |
|---|
| 202 | Single paragraph with '----' in it will be turned into separator: |
|---|
| 203 | |
|---|
| 204 | ----------- |
|---|
| 205 | |
|---|
| 206 | And this is the last paragraph in |
|---|
| 207 | the test. Be happy! |
|---|
| 208 | |
|---|
| 209 | ==================== |
|---|
| 210 | |
|---|
| 211 | ## Why? |
|---|
| 212 | |
|---|
| 213 | We wanted a markup language with the following requirements: |
|---|
| 214 | - less than 300 lines of functional code |
|---|
| 215 | - easy to read |
|---|
| 216 | - secure |
|---|
| 217 | - support table, ul, ol, code |
|---|
| 218 | - support html5 video and audio elements (html serialization only) |
|---|
| 219 | - can align images and resize them |
|---|
| 220 | - can specify class for tables, blockquotes and code elements |
|---|
| 221 | - can add anchors |
|---|
| 222 | - does not use _ for markup (since it creates odd behavior) |
|---|
| 223 | - automatically links urls |
|---|
| 224 | - fast |
|---|
| 225 | - easy to extend |
|---|
| 226 | - supports latex and pdf including references |
|---|
| 227 | - allows to describe the markup in the markup (this document is generated from markmin syntax) |
|---|
| 228 | |
|---|
| 229 | (results depend on text but in average for text ~100K markmin is 30% faster than markdown, for text ~10K it is 10x faster) |
|---|
| 230 | |
|---|
| 231 | The [[web2py book http://www.lulu.com/product/paperback/web2py-%283rd-edition%29/12822827]] published by lulu, for example, was entirely generated with markmin2pdf from the online [[web2py wiki http://www.web2py.com/book]] |
|---|
| 232 | |
|---|
| 233 | ## Download |
|---|
| 234 | |
|---|
| 235 | - http://web2py.googlecode.com/hg/gluon/contrib/markmin/markmin2html.py |
|---|
| 236 | - http://web2py.googlecode.com/hg/gluon/contrib/markmin/markmin2latex.py |
|---|
| 237 | - http://web2py.googlecode.com/hg/gluon/contrib/markmin/markmin2pdf.py |
|---|
| 238 | |
|---|
| 239 | markmin2html.py and markmin2latex.py are single files and have no web2py dependence. Their license is BSD. |
|---|
| 240 | |
|---|
| 241 | ## Examples |
|---|
| 242 | |
|---|
| 243 | ### Bold, italic, code and links |
|---|
| 244 | |
|---|
| 245 | ------------------------------------------------------------------------------ |
|---|
| 246 | **SOURCE** | **OUTPUT** |
|---|
| 247 | ============================================================================== |
|---|
| 248 | ``# title`` | **title** |
|---|
| 249 | ``## section`` | **section** |
|---|
| 250 | ``### subsection`` | **subsection** |
|---|
| 251 | ``**bold**`` | **bold** |
|---|
| 252 | ``''italic''`` | ''italic'' |
|---|
| 253 | ``~~strikeout~~`` | ~~strikeout~~ |
|---|
| 254 | ``!`!`verbatim`!`!`` | ``verbatim`` |
|---|
| 255 | ``\`\`color with **bold**\`\`:red`` | ``color with **bold**``:red |
|---|
| 256 | ``\`\`many colors\`\`:color[blue:#ffff00]`` | ``many colors``:color[blue:#ffff00] |
|---|
| 257 | ``http://google.com`` | http://google.com |
|---|
| 258 | ``[[**click** me #myanchor]]`` | [[**click** me #myanchor]] |
|---|
| 259 | ``[[click me [extra info] #myanchor popup]]`` | [[click me [extra info] #myanchor popup]] |
|---|
| 260 | ------------------------------------------------------------------------------- |
|---|
| 261 | |
|---|
| 262 | ### More on links |
|---|
| 263 | |
|---|
| 264 | The format is always ``[[title link]]`` or ``[[title [extra] link]]``. Notice you can nest bold, italic, strikeout and code inside the link ``title``. |
|---|
| 265 | |
|---|
| 266 | ### Anchors [[myanchor]] |
|---|
| 267 | |
|---|
| 268 | You can place an anchor anywhere in the text using the syntax ``[[name]]`` where ''name'' is the name of the anchor. |
|---|
| 269 | You can then link the anchor with [[link #myanchor]], i.e. ``[[link #myanchor]]`` or [[link with an extra info [extra info] #myanchor]], i.e. |
|---|
| 270 | ``[[link with an extra info [extra info] #myanchor]]``. |
|---|
| 271 | |
|---|
| 272 | ### Images |
|---|
| 273 | |
|---|
| 274 | [[alt-string for the image [the image title] http://www.web2py.com/examples/static/web2py_logo.png right 200px]] |
|---|
| 275 | This paragraph has an image aligned to the right with a width of 200px. Its is placed using the code |
|---|
| 276 | |
|---|
| 277 | ``[[alt-string for the image [the image title] http://www.web2py.com/examples/static/web2py_logo.png right 200px]]``. |
|---|
| 278 | |
|---|
| 279 | ### Unordered Lists |
|---|
| 280 | |
|---|
| 281 | `` |
|---|
| 282 | - Dog |
|---|
| 283 | - Cat |
|---|
| 284 | - Mouse |
|---|
| 285 | `` |
|---|
| 286 | |
|---|
| 287 | is rendered as |
|---|
| 288 | - Dog |
|---|
| 289 | - Cat |
|---|
| 290 | - Mouse |
|---|
| 291 | |
|---|
| 292 | Two new lines between items break the list in two lists. |
|---|
| 293 | |
|---|
| 294 | ### Ordered Lists |
|---|
| 295 | |
|---|
| 296 | `` |
|---|
| 297 | + Dog |
|---|
| 298 | + Cat |
|---|
| 299 | + Mouse |
|---|
| 300 | `` |
|---|
| 301 | |
|---|
| 302 | is rendered as |
|---|
| 303 | + Dog |
|---|
| 304 | + Cat |
|---|
| 305 | + Mouse |
|---|
| 306 | |
|---|
| 307 | |
|---|
| 308 | ### Multilevel Lists |
|---|
| 309 | |
|---|
| 310 | `` |
|---|
| 311 | + Dogs |
|---|
| 312 | -- red |
|---|
| 313 | -- brown |
|---|
| 314 | -- black |
|---|
| 315 | + Cats |
|---|
| 316 | -- fluffy |
|---|
| 317 | -- smooth |
|---|
| 318 | -- bald |
|---|
| 319 | + Mice |
|---|
| 320 | -- small |
|---|
| 321 | -- big |
|---|
| 322 | -- huge |
|---|
| 323 | `` |
|---|
| 324 | |
|---|
| 325 | is rendered as |
|---|
| 326 | + Dogs |
|---|
| 327 | -- red |
|---|
| 328 | -- brown |
|---|
| 329 | -- black |
|---|
| 330 | + Cats |
|---|
| 331 | -- fluffy |
|---|
| 332 | -- smooth |
|---|
| 333 | -- bald |
|---|
| 334 | + Mice |
|---|
| 335 | -- small |
|---|
| 336 | -- big |
|---|
| 337 | -- huge |
|---|
| 338 | |
|---|
| 339 | |
|---|
| 340 | ### Tables (with optional header and/or footer) |
|---|
| 341 | |
|---|
| 342 | Something like this |
|---|
| 343 | `` |
|---|
| 344 | ----------------- |
|---|
| 345 | **A**|**B**|**C** |
|---|
| 346 | ================= |
|---|
| 347 | 0 | 0 | X |
|---|
| 348 | 0 | X | 0 |
|---|
| 349 | X | 0 | 0 |
|---|
| 350 | ================= |
|---|
| 351 | **D**|**F**|**G** |
|---|
| 352 | -----------------:abc[id] |
|---|
| 353 | `` |
|---|
| 354 | is a table and is rendered as |
|---|
| 355 | ----------------- |
|---|
| 356 | **A**|**B**|**C** |
|---|
| 357 | ================= |
|---|
| 358 | 0 | 0 | X |
|---|
| 359 | 0 | X | 0 |
|---|
| 360 | X | 0 | 0 |
|---|
| 361 | ================= |
|---|
| 362 | **D**|**F**|**G** |
|---|
| 363 | -----------------:abc[id] |
|---|
| 364 | Four or more dashes delimit the table and | separates the columns. |
|---|
| 365 | The ``:abc``, ``:id[abc_1]`` or ``:abc[abc_1]`` at the end sets the class and/or id for the table and it is optional. |
|---|
| 366 | |
|---|
| 367 | ### Blockquote |
|---|
| 368 | |
|---|
| 369 | A table with a single cell is rendered as a blockquote: |
|---|
| 370 | |
|---|
| 371 | ----- |
|---|
| 372 | Hello world |
|---|
| 373 | ----- |
|---|
| 374 | |
|---|
| 375 | Blockquote can contain headers, paragraphs, lists and tables: |
|---|
| 376 | |
|---|
| 377 | `` |
|---|
| 378 | ----- |
|---|
| 379 | This is a paragraph in a blockquote |
|---|
| 380 | |
|---|
| 381 | + item 1 |
|---|
| 382 | + item 2 |
|---|
| 383 | -- item 2.1 |
|---|
| 384 | -- item 2.2 |
|---|
| 385 | + item 3 |
|---|
| 386 | |
|---|
| 387 | --------- |
|---|
| 388 | 0 | 0 | X |
|---|
| 389 | 0 | X | 0 |
|---|
| 390 | X | 0 | 0 |
|---|
| 391 | ---------:tableclass1 |
|---|
| 392 | ----- |
|---|
| 393 | `` |
|---|
| 394 | |
|---|
| 395 | is rendered as: |
|---|
| 396 | ----- |
|---|
| 397 | This is a paragraph in a blockquote |
|---|
| 398 | |
|---|
| 399 | + item 1 |
|---|
| 400 | + item 2 |
|---|
| 401 | -- item 2.1 |
|---|
| 402 | -- item 2.2 |
|---|
| 403 | + item 3 |
|---|
| 404 | |
|---|
| 405 | --------- |
|---|
| 406 | 0 | 0 | X |
|---|
| 407 | 0 | X | 0 |
|---|
| 408 | X | 0 | 0 |
|---|
| 409 | ---------:tableclass1 |
|---|
| 410 | ----- |
|---|
| 411 | |
|---|
| 412 | |
|---|
| 413 | ### Code, ``<code>``, escaping and extra stuff |
|---|
| 414 | |
|---|
| 415 | `` |
|---|
| 416 | def test(): |
|---|
| 417 | return "this is Python code" |
|---|
| 418 | ``:python |
|---|
| 419 | |
|---|
| 420 | Optionally a ` inside a ``!`!`...`!`!`` block can be inserted escaped with !`!. |
|---|
| 421 | |
|---|
| 422 | **NOTE:** You can escape markmin constructions (\\'\\',\`\`,\*\*,\~\~,\[,\{,\]\},\$,\@) with '\\\\' character: |
|---|
| 423 | so \\\\`\\\\` can replace !`!`! escape string |
|---|
| 424 | |
|---|
| 425 | The ``:python`` after the markup is also optional. If present, by default, it is used to set the class of the <code> block. |
|---|
| 426 | The behavior can be overridden by passing an argument ``extra`` to the ``render`` function. For example: |
|---|
| 427 | |
|---|
| 428 | `` |
|---|
| 429 | markmin2html("!`!!`!aaa!`!!`!:custom", |
|---|
| 430 | extra=dict(custom=lambda text: 'x'+text+'x')) |
|---|
| 431 | ``:python |
|---|
| 432 | |
|---|
| 433 | generates |
|---|
| 434 | |
|---|
| 435 | ``'xaaax'``:python |
|---|
| 436 | |
|---|
| 437 | (the ``!`!`...`!`!:custom`` block is rendered by the ``custom=lambda`` function passed to ``render``). |
|---|
| 438 | |
|---|
| 439 | ### Line breaks |
|---|
| 440 | |
|---|
| 441 | ``[[NEWLINE]]`` tag is used to break lines: |
|---|
| 442 | `` |
|---|
| 443 | #### Multiline [[NEWLINE]] |
|---|
| 444 | title |
|---|
| 445 | paragraph [[NEWLINE]] |
|---|
| 446 | with breaks[[NEWLINE]]in it |
|---|
| 447 | `` |
|---|
| 448 | generates: |
|---|
| 449 | |
|---|
| 450 | #### Multiline [[NEWLINE]] |
|---|
| 451 | title |
|---|
| 452 | paragraph [[NEWLINE]] |
|---|
| 453 | with breaks[[NEWLINE]]in it |
|---|
| 454 | |
|---|
| 455 | |
|---|
| 456 | ### Html5 support |
|---|
| 457 | |
|---|
| 458 | Markmin also supports the <video> and <audio> html5 tags using the notation: |
|---|
| 459 | `` |
|---|
| 460 | [[message link video]] |
|---|
| 461 | [[message link audio]] |
|---|
| 462 | |
|---|
| 463 | [[message [title] link video]] |
|---|
| 464 | [[message [title] link audio]] |
|---|
| 465 | `` |
|---|
| 466 | where ``message`` will be shown in browsers without HTML5 video/audio tags support. |
|---|
| 467 | |
|---|
| 468 | ### Latex and other extensions |
|---|
| 469 | |
|---|
| 470 | Formulas can be embedded into HTML with ''\$\$``formula``\$\$''. |
|---|
| 471 | You can use Google charts to render the formula: |
|---|
| 472 | |
|---|
| 473 | `` |
|---|
| 474 | LATEX = '<img src="http://chart.apis.google.com/chart?cht=tx&chl=%s" />' |
|---|
| 475 | markmin2html(text,{'latex':lambda code: LATEX % urllib.quote(code)}) |
|---|
| 476 | `` |
|---|
| 477 | |
|---|
| 478 | ### Code with syntax highlighting |
|---|
| 479 | |
|---|
| 480 | This requires a syntax highlighting tool, such as the web2py CODE helper. |
|---|
| 481 | |
|---|
| 482 | `` |
|---|
| 483 | extra={'code_cpp':lambda text: CODE(text,language='cpp').xml(), |
|---|
| 484 | 'code_java':lambda text: CODE(text,language='java').xml(), |
|---|
| 485 | 'code_python':lambda text: CODE(text,language='python').xml(), |
|---|
| 486 | 'code_html':lambda text: CODE(text,language='html').xml()} |
|---|
| 487 | `` |
|---|
| 488 | or simple: |
|---|
| 489 | `` |
|---|
| 490 | extra={'code':lambda text,lang='python': CODE(text,language=lang).xml()} |
|---|
| 491 | `` |
|---|
| 492 | `` |
|---|
| 493 | markmin2html(text,extra=extra) |
|---|
| 494 | `` |
|---|
| 495 | |
|---|
| 496 | Code can now be marked up as in this example: |
|---|
| 497 | `` |
|---|
| 498 | !`!` |
|---|
| 499 | <html><body>example</body></html> |
|---|
| 500 | !`!`:code_html |
|---|
| 501 | `` |
|---|
| 502 | OR |
|---|
| 503 | `` |
|---|
| 504 | !`!` |
|---|
| 505 | <html><body>example</body></html> |
|---|
| 506 | !`!`:code[html] |
|---|
| 507 | `` |
|---|
| 508 | |
|---|
| 509 | ### Citations and References |
|---|
| 510 | |
|---|
| 511 | Citations are treated as internal links in html and proper citations in latex if there is a final section called "References". Items like |
|---|
| 512 | |
|---|
| 513 | `` |
|---|
| 514 | - [[key]] value |
|---|
| 515 | `` |
|---|
| 516 | |
|---|
| 517 | in the References will be translated into Latex |
|---|
| 518 | |
|---|
| 519 | `` |
|---|
| 520 | \\bibitem{key} value |
|---|
| 521 | `` |
|---|
| 522 | |
|---|
| 523 | Here is an example of usage: |
|---|
| 524 | |
|---|
| 525 | `` |
|---|
| 526 | As shown in Ref.!`!`mdipierro`!`!:cite |
|---|
| 527 | |
|---|
| 528 | ## References |
|---|
| 529 | |
|---|
| 530 | - [[mdipierro]] web2py Manual, 3rd Edition, lulu.com |
|---|
| 531 | `` |
|---|
| 532 | |
|---|
| 533 | ### Caveats |
|---|
| 534 | |
|---|
| 535 | ``<ul/>``, ``<ol/>``, ``<code/>``, ``<table/>``, ``<blockquote/>``, ``<h1/>``, ..., ``<h6/>`` do not have ``<p>...</p>`` around them. |
|---|
| 536 | |
|---|
| 537 | """ |
|---|
| 538 | html_colors = ['aqua', 'black', 'blue', 'fuchsia', 'gray', 'green', |
|---|
| 539 | 'lime', 'maroon', 'navy', 'olive', 'purple', 'red', |
|---|
| 540 | 'silver', 'teal', 'white', 'yellow'] |
|---|
| 541 | |
|---|
| 542 | META = '\x06' |
|---|
| 543 | LINK = '\x07' |
|---|
| 544 | DISABLED_META = '\x08' |
|---|
| 545 | LATEX = '<img src="http://chart.apis.google.com/chart?cht=tx&chl=%s" />' |
|---|
| 546 | regex_URL = re.compile(r'@/(?P<a>\w*)/(?P<c>\w*)/(?P<f>\w*(\.\w+)?)(/(?P<args>[\w\.\-/]+))?') |
|---|
| 547 | regex_env2 = re.compile(r'@\{(?P<a>[\w\-\.]+?)(\:(?P<b>.*?))?\}') |
|---|
| 548 | regex_expand_meta = re.compile('(' + META + '|' + DISABLED_META + '|````)') |
|---|
| 549 | regex_dd = re.compile(r'\$\$(?P<latex>.*?)\$\$') |
|---|
| 550 | regex_code = re.compile( |
|---|
| 551 | '(' + META + '|' + DISABLED_META + r'|````)|(``(?P<t>.+?)``(?::(?P<c>[a-zA-Z][_a-zA-Z\-\d]*)(?:\[(?P<p>[^\]]*)\])?)?)', |
|---|
| 552 | re.S) |
|---|
| 553 | regex_strong = re.compile(r'\*\*(?P<t>[^\s*]+( +[^\s*]+)*)\*\*') |
|---|
| 554 | regex_del = re.compile(r'~~(?P<t>[^\s~]+( +[^\s~]+)*)~~') |
|---|
| 555 | regex_em = re.compile(r"''(?P<t>([^\s']| |'(?!'))+)''") |
|---|
| 556 | regex_num = re.compile(r"^\s*[+-]?((\d+(\.\d*)?)|\.\d+)([eE][+-]?[0-9]+)?\s*$") |
|---|
| 557 | regex_list = re.compile('^(?:(?:(#{1,6})|(?:(\.+|\++|\-+)(\.)?))\s*)?(.*)$') |
|---|
| 558 | regex_bq_headline = re.compile('^(?:(\.+|\++|\-+)(\.)?\s+)?(-{3}-*)$') |
|---|
| 559 | regex_tq = re.compile('^(-{3}-*)(?::(?P<c>[a-zA-Z][_a-zA-Z\-\d]*)(?:\[(?P<p>[a-zA-Z][_a-zA-Z\-\d]*)\])?)?$') |
|---|
| 560 | regex_proto = re.compile(r'(?<!["\w>/=])(?P<p>\w+):(?P<k>\w+://[\w\d\-+=?%&/:.]+)', re.M) |
|---|
| 561 | regex_auto = re.compile(r'(?<!["\w>/=])(?P<k>\w+://[\w\d\-+_=?%&/:.,;#]+\w|[\w\-.]+@[\w\-.]+)', re.M) |
|---|
| 562 | regex_link = re.compile(r'(' + LINK + r')|\[\[(?P<s>.+?)\]\]', re.S) |
|---|
| 563 | regex_link_level2 = re.compile(r'^(?P<t>\S.*?)?(?:\s+\[(?P<a>.+?)\])?(?:\s+(?P<k>\S+))?(?:\s+(?P<p>popup))?\s*$', re.S) |
|---|
| 564 | regex_media_level2 = re.compile( |
|---|
| 565 | r'^(?P<t>\S.*?)?(?:\s+\[(?P<a>.+?)\])?(?:\s+(?P<k>\S+))?\s+(?P<p>img|IMG|left|right|center|video|audio|blockleft|blockright)(?:\s+(?P<w>\d+px))?\s*$', |
|---|
| 566 | re.S) |
|---|
| 567 | |
|---|
| 568 | regex_markmin_escape = re.compile(r"(\\*)(['`:*~\\[\]{}@\$+\-.#\n])") |
|---|
| 569 | regex_backslash = re.compile(r"\\(['`:*~\\[\]{}@\$+\-.#\n])") |
|---|
| 570 | ttab_in = maketrans("'`:*~\\[]{}@$+-.#\n", '\x0b\x0c\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x05') |
|---|
| 571 | ttab_out = maketrans('\x0b\x0c\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x05', "'`:*~\\[]{}@$+-.#\n") |
|---|
| 572 | regex_quote = re.compile('(?P<name>\w+?)\s*\=\s*') |
|---|
| 573 | |
|---|
| 574 | def local_html_escape(data, quote=False): |
|---|
| 575 | """ |
|---|
| 576 | Works with bytes. |
|---|
| 577 | Replace special characters "&", "<" and ">" to HTML-safe sequences. |
|---|
| 578 | If the optional flag quote is true (the default), the quotation mark |
|---|
| 579 | characters, both double quote (") and single quote (') characters are also |
|---|
| 580 | translated. |
|---|
| 581 | """ |
|---|
| 582 | if PY2: |
|---|
| 583 | import cgi |
|---|
| 584 | data = cgi.escape(data, quote) |
|---|
| 585 | return data.replace("'", "'") if quote else data |
|---|
| 586 | else: |
|---|
| 587 | import html |
|---|
| 588 | if isinstance(data, str): |
|---|
| 589 | return html.escape(data, quote=quote) |
|---|
| 590 | data = data.replace(b"&", b"&") # Must be done first! |
|---|
| 591 | data = data.replace(b"<", b"<") |
|---|
| 592 | data = data.replace(b">", b">") |
|---|
| 593 | if quote: |
|---|
| 594 | data = data.replace(b'"', b""") |
|---|
| 595 | data = data.replace(b'\'', b"'") |
|---|
| 596 | return data |
|---|
| 597 | |
|---|
| 598 | def make_dict(b): |
|---|
| 599 | return '{%s}' % regex_quote.sub("'\g<name>':", b) |
|---|
| 600 | |
|---|
| 601 | |
|---|
| 602 | def safe_eval(node_or_string, env): |
|---|
| 603 | """ |
|---|
| 604 | Safely evaluate an expression node or a string containing a Python |
|---|
| 605 | expression. The string or node provided may only consist of the following |
|---|
| 606 | Python literal structures: strings, numbers, tuples, lists, dicts, booleans, |
|---|
| 607 | and None. |
|---|
| 608 | """ |
|---|
| 609 | _safe_names = {'None': None, 'True': True, 'False': False} |
|---|
| 610 | _safe_names.update(env) |
|---|
| 611 | if isinstance(node_or_string, basestring): |
|---|
| 612 | node_or_string = ast.parse(node_or_string, mode='eval') |
|---|
| 613 | if isinstance(node_or_string, ast.Expression): |
|---|
| 614 | node_or_string = node_or_string.body |
|---|
| 615 | |
|---|
| 616 | def _convert(node): |
|---|
| 617 | if isinstance(node, ast.Str): |
|---|
| 618 | return node.s |
|---|
| 619 | elif isinstance(node, ast.Num): |
|---|
| 620 | return node.n |
|---|
| 621 | elif isinstance(node, ast.Tuple): |
|---|
| 622 | return tuple(map(_convert, node.elts)) |
|---|
| 623 | elif isinstance(node, ast.List): |
|---|
| 624 | return list(map(_convert, node.elts)) |
|---|
| 625 | elif isinstance(node, ast.Dict): |
|---|
| 626 | return dict((_convert(k), _convert(v)) for k, v |
|---|
| 627 | in zip(node.keys, node.values)) |
|---|
| 628 | elif isinstance(node, ast.Name): |
|---|
| 629 | if node.id in _safe_names: |
|---|
| 630 | return _safe_names[node.id] |
|---|
| 631 | elif isinstance(node, ast.BinOp) and \ |
|---|
| 632 | isinstance(node.op, (ast.Add, ast.Sub)) and \ |
|---|
| 633 | isinstance(node.right, ast.Num) and \ |
|---|
| 634 | isinstance(node.right.n, complex) and \ |
|---|
| 635 | isinstance(node.left, ast.Num) and \ |
|---|
| 636 | isinstance(node.left.n, (int, long, float)): |
|---|
| 637 | left = node.left.n |
|---|
| 638 | right = node.right.n |
|---|
| 639 | if isinstance(node.op, ast.Add): |
|---|
| 640 | return left + right |
|---|
| 641 | else: |
|---|
| 642 | return left - right |
|---|
| 643 | raise ValueError('malformed string') |
|---|
| 644 | |
|---|
| 645 | return _convert(node_or_string) |
|---|
| 646 | |
|---|
| 647 | |
|---|
| 648 | def markmin_escape(text): |
|---|
| 649 | """ insert \\ before markmin control characters: '`:*~[]{}@$ """ |
|---|
| 650 | return regex_markmin_escape.sub( |
|---|
| 651 | lambda m: '\\' + m.group(0).replace('\\', '\\\\'), text) |
|---|
| 652 | |
|---|
| 653 | |
|---|
| 654 | def replace_autolinks(text, autolinks): |
|---|
| 655 | return regex_auto.sub(lambda m: autolinks(m.group('k')), text) |
|---|
| 656 | |
|---|
| 657 | |
|---|
| 658 | def replace_at_urls(text, url): |
|---|
| 659 | # this is experimental @{function/args} |
|---|
| 660 | def u1(match, url=url): |
|---|
| 661 | a, c, f, args = match.group('a', 'c', 'f', 'args') |
|---|
| 662 | return url(a=a or None, c=c or None, f=f or None, |
|---|
| 663 | args=(args or '').split('/'), scheme=True, host=True) |
|---|
| 664 | |
|---|
| 665 | return regex_URL.sub(u1, text) |
|---|
| 666 | |
|---|
| 667 | |
|---|
| 668 | def replace_components(text, env): |
|---|
| 669 | # not perfect but acceptable |
|---|
| 670 | def u2(match, env=env): |
|---|
| 671 | f = env.get(match.group('a'), match.group(0)) |
|---|
| 672 | if callable(f): |
|---|
| 673 | b = match.group('b') |
|---|
| 674 | try: |
|---|
| 675 | b = safe_eval(make_dict(b), env) |
|---|
| 676 | except: |
|---|
| 677 | pass |
|---|
| 678 | try: |
|---|
| 679 | f = f(**b) if isinstance(b, dict) else f(b) |
|---|
| 680 | except Exception as e: |
|---|
| 681 | f = 'ERROR: %s' % e |
|---|
| 682 | return str(f) |
|---|
| 683 | |
|---|
| 684 | text = regex_env2.sub(u2, text) |
|---|
| 685 | return text |
|---|
| 686 | |
|---|
| 687 | |
|---|
| 688 | def autolinks_simple(url): |
|---|
| 689 | """ |
|---|
| 690 | it automatically converts the url to link, |
|---|
| 691 | image, video or audio tag |
|---|
| 692 | """ |
|---|
| 693 | u_url = url.lower() |
|---|
| 694 | if '@' in url and '://' not in url: |
|---|
| 695 | return '<a href="mailto:%s">%s</a>' % (url, url) |
|---|
| 696 | elif u_url.endswith(('.jpg', '.jpeg', '.gif', '.png')): |
|---|
| 697 | return '<img src="%s" controls />' % url |
|---|
| 698 | elif u_url.endswith(('.mp4', '.mpeg', '.mov', '.ogv')): |
|---|
| 699 | return '<video src="%s" controls></video>' % url |
|---|
| 700 | elif u_url.endswith(('.mp3', '.wav', '.ogg')): |
|---|
| 701 | return '<audio src="%s" controls></audio>' % url |
|---|
| 702 | return '<a href="%s">%s</a>' % (url, url) |
|---|
| 703 | |
|---|
| 704 | |
|---|
| 705 | def protolinks_simple(proto, url): |
|---|
| 706 | """ |
|---|
| 707 | it converts url to html-string using appropriate proto-prefix: |
|---|
| 708 | Uses for construction "proto:url", e.g.: |
|---|
| 709 | "iframe:http://www.example.com/path" will call protolinks() |
|---|
| 710 | with parameters: |
|---|
| 711 | proto="iframe" |
|---|
| 712 | url="http://www.example.com/path" |
|---|
| 713 | """ |
|---|
| 714 | if proto in ('iframe', 'embed'): # == 'iframe': |
|---|
| 715 | return '<iframe src="%s" frameborder="0" allowfullscreen></iframe>' % url |
|---|
| 716 | # elif proto == 'embed': # NOTE: embed is a synonym to iframe now |
|---|
| 717 | # return '<a href="%s" class="%sembed">%s></a>'%(url,class_prefix,url) |
|---|
| 718 | elif proto == 'qr': |
|---|
| 719 | return '<img style="width:100px" src="http://chart.apis.google.com/chart?cht=qr&chs=100x100&chl=%s&choe=UTF-8&chld=H" alt="QR Code" title="QR Code" />' % url |
|---|
| 720 | return proto + ':' + url |
|---|
| 721 | |
|---|
| 722 | |
|---|
| 723 | def email_simple(email): |
|---|
| 724 | return '<a href="mailto:%s">%s</a>' % (email, email) |
|---|
| 725 | |
|---|
| 726 | |
|---|
| 727 | def render(text, |
|---|
| 728 | extra={}, |
|---|
| 729 | allowed={}, |
|---|
| 730 | sep='p', |
|---|
| 731 | URL=None, |
|---|
| 732 | environment=None, |
|---|
| 733 | latex='google', |
|---|
| 734 | autolinks='default', |
|---|
| 735 | protolinks='default', |
|---|
| 736 | class_prefix='', |
|---|
| 737 | id_prefix='markmin_', |
|---|
| 738 | pretty_print=False): |
|---|
| 739 | """ |
|---|
| 740 | Arguments: |
|---|
| 741 | - text is the text to be processed |
|---|
| 742 | - extra is a dict like extra=dict(custom=lambda value: value) that process custom code |
|---|
| 743 | as in " ``this is custom code``:custom " |
|---|
| 744 | - allowed is a dictionary of list of allowed classes like |
|---|
| 745 | allowed = dict(code=('python','cpp','java')) |
|---|
| 746 | - sep can be 'p' to separate text in <p>...</p> |
|---|
| 747 | or can be 'br' to separate text using <br /> |
|---|
| 748 | - URL - |
|---|
| 749 | - environment is a dictionary of environment variables (can be accessed with @{variable} |
|---|
| 750 | - latex - |
|---|
| 751 | - autolinks is a function to convert auto urls to html-code (default is autolinks(url) ) |
|---|
| 752 | - protolinks is a function to convert proto-urls (e.g."proto:url") to html-code |
|---|
| 753 | (default is protolinks(proto,url)) |
|---|
| 754 | - class_prefix is a prefix for ALL classes in markmin text. E.g. if class_prefix='my_' |
|---|
| 755 | then for ``test``:cls class will be changed to "my_cls" (default value is '') |
|---|
| 756 | - id_prefix is prefix for ALL ids in markmin text (default value is 'markmin_'). E.g.: |
|---|
| 757 | -- [[id]] will be converted to <span class="anchor" id="markmin_id"></span> |
|---|
| 758 | -- [[link #id]] will be converted to <a href="#markmin_id">link</a> |
|---|
| 759 | -- ``test``:cls[id] will be converted to <code class="cls" id="markmin_id">test</code> |
|---|
| 760 | |
|---|
| 761 | >>> render('this is\\n# a section\\n\\nparagraph') |
|---|
| 762 | '<p>this is</p><h1>a section</h1><p>paragraph</p>' |
|---|
| 763 | >>> render('this is\\n## a subsection\\n\\nparagraph') |
|---|
| 764 | '<p>this is</p><h2>a subsection</h2><p>paragraph</p>' |
|---|
| 765 | >>> render('this is\\n### a subsubsection\\n\\nparagraph') |
|---|
| 766 | '<p>this is</p><h3>a subsubsection</h3><p>paragraph</p>' |
|---|
| 767 | >>> render('**hello world**') |
|---|
| 768 | '<p><strong>hello world</strong></p>' |
|---|
| 769 | >>> render('``hello world``') |
|---|
| 770 | '<code>hello world</code>' |
|---|
| 771 | >>> render('``hello world``:python') |
|---|
| 772 | '<code class="python">hello world</code>' |
|---|
| 773 | >>> render('``\\nhello\\nworld\\n``:python') |
|---|
| 774 | '<pre><code class="python">hello\\nworld</code></pre>' |
|---|
| 775 | >>> render('``hello world``:python[test_id]') |
|---|
| 776 | '<code class="python" id="markmin_test_id">hello world</code>' |
|---|
| 777 | >>> render('``hello world``:id[test_id]') |
|---|
| 778 | '<code id="markmin_test_id">hello world</code>' |
|---|
| 779 | >>> render('``\\nhello\\nworld\\n``:python[test_id]') |
|---|
| 780 | '<pre><code class="python" id="markmin_test_id">hello\\nworld</code></pre>' |
|---|
| 781 | >>> render('``\\nhello\\nworld\\n``:id[test_id]') |
|---|
| 782 | '<pre><code id="markmin_test_id">hello\\nworld</code></pre>' |
|---|
| 783 | >>> render("''hello world''") |
|---|
| 784 | '<p><em>hello world</em></p>' |
|---|
| 785 | >>> render('** hello** **world**') |
|---|
| 786 | '<p>** hello** <strong>world</strong></p>' |
|---|
| 787 | |
|---|
| 788 | >>> render('- this\\n- is\\n- a list\\n\\nand this\\n- is\\n- another') |
|---|
| 789 | '<ul><li>this</li><li>is</li><li>a list</li></ul><p>and this</p><ul><li>is</li><li>another</li></ul>' |
|---|
| 790 | |
|---|
| 791 | >>> render('+ this\\n+ is\\n+ a list\\n\\nand this\\n+ is\\n+ another') |
|---|
| 792 | '<ol><li>this</li><li>is</li><li>a list</li></ol><p>and this</p><ol><li>is</li><li>another</li></ol>' |
|---|
| 793 | |
|---|
| 794 | >>> render("----\\na | b\\nc | d\\n----\\n") |
|---|
| 795 | '<table><tbody><tr class="first"><td>a</td><td>b</td></tr><tr class="even"><td>c</td><td>d</td></tr></tbody></table>' |
|---|
| 796 | |
|---|
| 797 | >>> render("----\\nhello world\\n----\\n") |
|---|
| 798 | '<blockquote><p>hello world</p></blockquote>' |
|---|
| 799 | |
|---|
| 800 | >>> render('[[myanchor]]') |
|---|
| 801 | '<p><span class="anchor" id="markmin_myanchor"></span></p>' |
|---|
| 802 | |
|---|
| 803 | >>> render('[[ http://example.com]]') |
|---|
| 804 | '<p><a href="http://example.com">http://example.com</a></p>' |
|---|
| 805 | |
|---|
| 806 | >>> render('[[bookmark [http://example.com] ]]') |
|---|
| 807 | '<p><span class="anchor" id="markmin_bookmark"><a href="http://example.com">http://example.com</a></span></p>' |
|---|
| 808 | |
|---|
| 809 | >>> render('[[this is a link http://example.com]]') |
|---|
| 810 | '<p><a href="http://example.com">this is a link</a></p>' |
|---|
| 811 | |
|---|
| 812 | >>> render('[[this is an image http://example.com left]]') |
|---|
| 813 | '<p><img src="http://example.com" alt="this is an image" style="float:left" /></p>' |
|---|
| 814 | |
|---|
| 815 | >>> render('[[this is an image http://example.com left 200px]]') |
|---|
| 816 | '<p><img src="http://example.com" alt="this is an image" style="float:left;width:200px" /></p>' |
|---|
| 817 | |
|---|
| 818 | >>> render("[[Your browser doesn't support <video> HTML5 tag http://example.com video]]") |
|---|
| 819 | '<p><video controls="controls"><source src="http://example.com" />Your browser doesn\\'t support <video> HTML5 tag</video></p>' |
|---|
| 820 | |
|---|
| 821 | >>> render("[[Your browser doesn't support <audio> HTML5 tag http://example.com audio]]") |
|---|
| 822 | '<p><audio controls="controls"><source src="http://example.com" />Your browser doesn\\'t support <audio> HTML5 tag</audio></p>' |
|---|
| 823 | |
|---|
| 824 | >>> render("[[Your\\nbrowser\\ndoesn't\\nsupport\\n<audio> HTML5 tag http://exam\\\\\\nple.com\\naudio]]") |
|---|
| 825 | '<p><audio controls="controls"><source src="http://example.com" />Your browser doesn\\'t support <audio> HTML5 tag</audio></p>' |
|---|
| 826 | |
|---|
| 827 | >>> render('[[this is a **link** http://example.com]]') |
|---|
| 828 | '<p><a href="http://example.com">this is a <strong>link</strong></a></p>' |
|---|
| 829 | |
|---|
| 830 | >>> render("``aaa``:custom", extra=dict(custom=lambda text: 'x'+text+'x')) |
|---|
| 831 | 'xaaax' |
|---|
| 832 | |
|---|
| 833 | >>> print(render(r"$$\int_a^b sin(x)dx$$")) |
|---|
| 834 | <img src="http://chart.apis.google.com/chart?cht=tx&chl=%5Cint_a%5Eb%20sin%28x%29dx" /> |
|---|
| 835 | |
|---|
| 836 | >>> markmin2html(r"use backslash: \[\[[[mess\[[ag\]]e link]]\]]") |
|---|
| 837 | '<p>use backslash: [[<a href="link">mess[[ag]]e</a>]]</p>' |
|---|
| 838 | |
|---|
| 839 | >>> markmin2html("backslash instead of exclamation sign: \``probe``") |
|---|
| 840 | '<p>backslash instead of exclamation sign: ``probe``</p>' |
|---|
| 841 | |
|---|
| 842 | >>> render(r"simple image: [[\[[this is an image\]] http://example.com IMG]]!!!") |
|---|
| 843 | '<p>simple image: <img src="http://example.com" alt="[[this is an image]]" />!!!</p>' |
|---|
| 844 | |
|---|
| 845 | >>> render(r"simple link no anchor with popup: [[ http://example.com popup]]") |
|---|
| 846 | '<p>simple link no anchor with popup: <a href="http://example.com" target="_blank">http://example.com</a></p>' |
|---|
| 847 | |
|---|
| 848 | >>> render("auto-url: http://example.com") |
|---|
| 849 | '<p>auto-url: <a href="http://example.com">http://example.com</a></p>' |
|---|
| 850 | |
|---|
| 851 | >>> render("auto-image: (http://example.com/image.jpeg)") |
|---|
| 852 | '<p>auto-image: (<img src="http://example.com/image.jpeg" controls />)</p>' |
|---|
| 853 | |
|---|
| 854 | >>> render("qr: (qr:http://example.com/image.jpeg)") |
|---|
| 855 | '<p>qr: (<img style="width:100px" src="http://chart.apis.google.com/chart?cht=qr&chs=100x100&chl=http://example.com/image.jpeg&choe=UTF-8&chld=H" alt="QR Code" title="QR Code" />)</p>' |
|---|
| 856 | |
|---|
| 857 | >>> render("embed: (embed:http://example.com/page)") |
|---|
| 858 | '<p>embed: (<iframe src="http://example.com/page" frameborder="0" allowfullscreen></iframe>)</p>' |
|---|
| 859 | |
|---|
| 860 | >>> render("iframe: (iframe:http://example.com/page)") |
|---|
| 861 | '<p>iframe: (<iframe src="http://example.com/page" frameborder="0" allowfullscreen></iframe>)</p>' |
|---|
| 862 | |
|---|
| 863 | >>> render("title1: [[test message [simple \[test\] title] http://example.com ]] test") |
|---|
| 864 | '<p>title1: <a href="http://example.com" title="simple [test] title">test message</a> test</p>' |
|---|
| 865 | |
|---|
| 866 | >>> render("title2: \[\[[[test message [simple title] http://example.com popup]]\]]") |
|---|
| 867 | '<p>title2: [[<a href="http://example.com" title="simple title" target="_blank">test message</a>]]</p>' |
|---|
| 868 | |
|---|
| 869 | >>> render("title3: [[ [link w/o anchor but with title] http://www.example.com ]]") |
|---|
| 870 | '<p>title3: <a href="http://www.example.com" title="link w/o anchor but with title">http://www.example.com</a></p>' |
|---|
| 871 | |
|---|
| 872 | >>> render("title4: [[ [simple title] http://www.example.com popup]]") |
|---|
| 873 | '<p>title4: <a href="http://www.example.com" title="simple title" target="_blank">http://www.example.com</a></p>' |
|---|
| 874 | |
|---|
| 875 | >>> render("title5: [[test message [simple title] http://example.com IMG]]") |
|---|
| 876 | '<p>title5: <img src="http://example.com" alt="test message" title="simple title" /></p>' |
|---|
| 877 | |
|---|
| 878 | >>> render("title6: [[[test message w/o title] http://example.com IMG]]") |
|---|
| 879 | '<p>title6: <img src="http://example.com" alt="[test message w/o title]" /></p>' |
|---|
| 880 | |
|---|
| 881 | >>> render("title7: [[[this is not a title] [this is a title] http://example.com IMG]]") |
|---|
| 882 | '<p>title7: <img src="http://example.com" alt="[this is not a title]" title="this is a title" /></p>' |
|---|
| 883 | |
|---|
| 884 | >>> render("title8: [[test message [title] http://example.com center]]") |
|---|
| 885 | '<p>title8: <p style="text-align:center"><img src="http://example.com" alt="test message" title="title" /></p></p>' |
|---|
| 886 | |
|---|
| 887 | >>> render("title9: [[test message [title] http://example.com left]]") |
|---|
| 888 | '<p>title9: <img src="http://example.com" alt="test message" title="title" style="float:left" /></p>' |
|---|
| 889 | |
|---|
| 890 | >>> render("title10: [[test message [title] http://example.com right 100px]]") |
|---|
| 891 | '<p>title10: <img src="http://example.com" alt="test message" title="title" style="float:right;width:100px" /></p>' |
|---|
| 892 | |
|---|
| 893 | >>> render("title11: [[test message [title] http://example.com center 200px]]") |
|---|
| 894 | '<p>title11: <p style="text-align:center"><img src="http://example.com" alt="test message" title="title" style="width:200px" /></p></p>' |
|---|
| 895 | |
|---|
| 896 | >>> render(r"\\[[probe]]") |
|---|
| 897 | '<p>[[probe]]</p>' |
|---|
| 898 | |
|---|
| 899 | >>> render(r"\\\\[[probe]]") |
|---|
| 900 | '<p>\\\\<span class="anchor" id="markmin_probe"></span></p>' |
|---|
| 901 | |
|---|
| 902 | >>> render(r"\\\\\\[[probe]]") |
|---|
| 903 | '<p>\\\\[[probe]]</p>' |
|---|
| 904 | |
|---|
| 905 | >>> render(r"\\\\\\\\[[probe]]") |
|---|
| 906 | '<p>\\\\\\\\<span class="anchor" id="markmin_probe"></span></p>' |
|---|
| 907 | |
|---|
| 908 | >>> render(r"\\\\\\\\\[[probe]]") |
|---|
| 909 | '<p>\\\\\\\\[[probe]]</p>' |
|---|
| 910 | |
|---|
| 911 | >>> render(r"\\\\\\\\\\\[[probe]]") |
|---|
| 912 | '<p>\\\\\\\\\\\\<span class="anchor" id="markmin_probe"></span></p>' |
|---|
| 913 | |
|---|
| 914 | >>> render("``[[ [\\[[probe\]\\]] URL\\[x\\]]]``:red[dummy_params]") |
|---|
| 915 | '<span style="color: red"><a href="URL[x]" title="[[probe]]">URL[x]</a></span>' |
|---|
| 916 | |
|---|
| 917 | >>> render("the \\**text**") |
|---|
| 918 | '<p>the **text**</p>' |
|---|
| 919 | |
|---|
| 920 | >>> render("the \\``text``") |
|---|
| 921 | '<p>the ``text``</p>' |
|---|
| 922 | |
|---|
| 923 | >>> render("the \\\\''text''") |
|---|
| 924 | "<p>the ''text''</p>" |
|---|
| 925 | |
|---|
| 926 | >>> render("the [[link [**with** ``<b>title</b>``:red] http://www.example.com]]") |
|---|
| 927 | '<p>the <a href="http://www.example.com" title="**with** ``<b>title</b>``:red">link</a></p>' |
|---|
| 928 | |
|---|
| 929 | >>> render("the [[link \\[**without** ``<b>title</b>``:red\\] http://www.example.com]]") |
|---|
| 930 | '<p>the <a href="http://www.example.com">link [<strong>without</strong> <span style="color: red"><b>title</b></span>]</a></p>' |
|---|
| 931 | |
|---|
| 932 | >>> render("aaa-META-``code``:text[]-LINK-[[link http://www.example.com]]-LINK-[[image http://www.picture.com img]]-end") |
|---|
| 933 | '<p>aaa-META-<code class="text">code</code>-LINK-<a href="http://www.example.com">link</a>-LINK-<img src="http://www.picture.com" alt="image" />-end</p>' |
|---|
| 934 | |
|---|
| 935 | >>> render("[[<a>test</a> [<a>test2</a>] <a>text3</a>]]") |
|---|
| 936 | '<p><a href="<a>text3</a>" title="<a>test2</a>"><a>test</a></a></p>' |
|---|
| 937 | |
|---|
| 938 | >>> render("[[<a>test</a> [<a>test2</a>] <a>text3</a> IMG]]") |
|---|
| 939 | '<p><img src="<a>text3</a>" alt="<a>test</a>" title="<a>test2</a>" /></p>' |
|---|
| 940 | |
|---|
| 941 | >>> render("**bold** ''italic'' ~~strikeout~~") |
|---|
| 942 | '<p><strong>bold</strong> <em>italic</em> <del>strikeout</del></p>' |
|---|
| 943 | |
|---|
| 944 | >>> render("this is ``a red on yellow text``:c[#FF0000:#FFFF00]") |
|---|
| 945 | '<p>this is <span style="color: #FF0000;background-color: #FFFF00;">a red on yellow text</span></p>' |
|---|
| 946 | |
|---|
| 947 | >>> render("this is ``a text with yellow background``:c[:yellow]") |
|---|
| 948 | '<p>this is <span style="background-color: yellow;">a text with yellow background</span></p>' |
|---|
| 949 | |
|---|
| 950 | >>> render("this is ``a colored text (RoyalBlue)``:color[rgb(65,105,225)]") |
|---|
| 951 | '<p>this is <span style="color: rgb(65,105,225);">a colored text (RoyalBlue)</span></p>' |
|---|
| 952 | |
|---|
| 953 | >>> render("this is ``a green text``:color[green:]") |
|---|
| 954 | '<p>this is <span style="color: green;">a green text</span></p>' |
|---|
| 955 | |
|---|
| 956 | >>> render("**@{probe:1}**", environment=dict(probe=lambda t:"test %s" % t)) |
|---|
| 957 | '<p><strong>test 1</strong></p>' |
|---|
| 958 | |
|---|
| 959 | >>> render("**@{probe:t=a}**", environment=dict(probe=lambda t:"test %s" % t, a=1)) |
|---|
| 960 | '<p><strong>test 1</strong></p>' |
|---|
| 961 | |
|---|
| 962 | >>> render('[[id1 [span **messag** in ''markmin''] ]] ... [[**link** to id [link\\\'s title] #mark1]]') |
|---|
| 963 | '<p><span class="anchor" id="markmin_id1">span <strong>messag</strong> in markmin</span> ... <a href="#markmin_mark1" title="link\\\'s title"><strong>link</strong> to id</a></p>' |
|---|
| 964 | |
|---|
| 965 | >>> render('# Multiline[[NEWLINE]]\\n title\\nParagraph[[NEWLINE]]\\nwith breaks[[NEWLINE]]\\nin it') |
|---|
| 966 | '<h1>Multiline<br /> title</h1><p>Paragraph<br /> with breaks<br /> in it</p>' |
|---|
| 967 | |
|---|
| 968 | >>> render("anchor with name 'NEWLINE': [[NEWLINE [ ] ]]") |
|---|
| 969 | '<p>anchor with name \\'NEWLINE\\': <span class="anchor" id="markmin_NEWLINE"></span></p>' |
|---|
| 970 | |
|---|
| 971 | >>> render("anchor with name 'NEWLINE': [[NEWLINE [newline] ]]") |
|---|
| 972 | '<p>anchor with name \\'NEWLINE\\': <span class="anchor" id="markmin_NEWLINE">newline</span></p>' |
|---|
| 973 | """ |
|---|
| 974 | if autolinks == "default": |
|---|
| 975 | autolinks = autolinks_simple |
|---|
| 976 | if protolinks == "default": |
|---|
| 977 | protolinks = protolinks_simple |
|---|
| 978 | pp = '\n' if pretty_print else '' |
|---|
| 979 | text = text if text is None or isinstance(text, str) else text.decode('utf8', 'strict') |
|---|
| 980 | |
|---|
| 981 | if not (isinstance(text, str)): |
|---|
| 982 | text = str(text or '') |
|---|
| 983 | text = regex_backslash.sub(lambda m: m.group(1).translate(ttab_in), text) |
|---|
| 984 | text = text.replace('\x05', '').replace('\r\n', '\n') # concatenate strings separeted by \\n |
|---|
| 985 | if URL is not None: |
|---|
| 986 | text = replace_at_urls(text, URL) |
|---|
| 987 | |
|---|
| 988 | if latex == 'google': |
|---|
| 989 | text = regex_dd.sub('``\g<latex>``:latex ', text) |
|---|
| 990 | |
|---|
| 991 | ############################################################# |
|---|
| 992 | # replace all blocks marked with ``...``:class[id] with META |
|---|
| 993 | # store them into segments they will be treated as code |
|---|
| 994 | ############################################################# |
|---|
| 995 | segments = [] |
|---|
| 996 | |
|---|
| 997 | def mark_code(m): |
|---|
| 998 | g = m.group(0) |
|---|
| 999 | if g in (META, DISABLED_META): |
|---|
| 1000 | segments.append((None, None, None, g)) |
|---|
| 1001 | return m.group() |
|---|
| 1002 | elif g == '````': |
|---|
| 1003 | segments.append((None, None, None, '')) |
|---|
| 1004 | return m.group() |
|---|
| 1005 | else: |
|---|
| 1006 | c = m.group('c') or '' |
|---|
| 1007 | p = m.group('p') or '' |
|---|
| 1008 | if 'code' in allowed and c not in allowed['code']: |
|---|
| 1009 | c = '' |
|---|
| 1010 | code = m.group('t').replace('!`!', '`') |
|---|
| 1011 | segments.append((code, c, p, m.group(0))) |
|---|
| 1012 | return META |
|---|
| 1013 | |
|---|
| 1014 | text = regex_code.sub(mark_code, text) |
|---|
| 1015 | |
|---|
| 1016 | ############################################################# |
|---|
| 1017 | # replace all blocks marked with [[...]] with LINK |
|---|
| 1018 | # store them into links they will be treated as link |
|---|
| 1019 | ############################################################# |
|---|
| 1020 | links = [] |
|---|
| 1021 | |
|---|
| 1022 | def mark_link(m): |
|---|
| 1023 | links.append(None if m.group() == LINK |
|---|
| 1024 | else m.group('s')) |
|---|
| 1025 | return LINK |
|---|
| 1026 | |
|---|
| 1027 | text = regex_link.sub(mark_link, text) |
|---|
| 1028 | text = local_html_escape(text) |
|---|
| 1029 | |
|---|
| 1030 | if protolinks: |
|---|
| 1031 | text = regex_proto.sub(lambda m: protolinks(*m.group('p', 'k')), text) |
|---|
| 1032 | |
|---|
| 1033 | if autolinks: |
|---|
| 1034 | text = replace_autolinks(text, autolinks) |
|---|
| 1035 | |
|---|
| 1036 | ############################################################# |
|---|
| 1037 | # normalize spaces |
|---|
| 1038 | ############################################################# |
|---|
| 1039 | strings = text.split('\n') |
|---|
| 1040 | |
|---|
| 1041 | def parse_title(t, s): # out, lev, etags, tag, s): |
|---|
| 1042 | hlevel = str(len(t)) |
|---|
| 1043 | out.extend(etags[::-1]) |
|---|
| 1044 | out.append("<h%s>%s" % (hlevel, s)) |
|---|
| 1045 | etags[:] = ["</h%s>%s" % (hlevel, pp)] |
|---|
| 1046 | lev = 0 |
|---|
| 1047 | ltags[:] = [] |
|---|
| 1048 | tlev[:] = [] |
|---|
| 1049 | return (lev, 'h') |
|---|
| 1050 | |
|---|
| 1051 | def parse_list(t, p, s, tag, lev, mtag, lineno): |
|---|
| 1052 | lent = len(t) |
|---|
| 1053 | if lent < lev: # current item level < previous item level |
|---|
| 1054 | while ltags[-1] > lent: |
|---|
| 1055 | ltags.pop() |
|---|
| 1056 | out.append(etags.pop()) |
|---|
| 1057 | lev = lent |
|---|
| 1058 | tlev[lev:] = [] |
|---|
| 1059 | |
|---|
| 1060 | if lent > lev: # current item level > previous item level |
|---|
| 1061 | if lev == 0: # previous line is not a list (paragraph or title) |
|---|
| 1062 | out.extend(etags[::-1]) |
|---|
| 1063 | ltags[:] = [] |
|---|
| 1064 | tlev[:] = [] |
|---|
| 1065 | etags[:] = [] |
|---|
| 1066 | if pend and mtag == '.': # paragraph in a list: |
|---|
| 1067 | out.append(etags.pop()) |
|---|
| 1068 | ltags.pop() |
|---|
| 1069 | for i in range(lent - lev): |
|---|
| 1070 | out.append('<' + tag + '>' + pp) |
|---|
| 1071 | etags.append('</' + tag + '>' + pp) |
|---|
| 1072 | lev += 1 |
|---|
| 1073 | ltags.append(lev) |
|---|
| 1074 | tlev.append(tag) |
|---|
| 1075 | elif lent == lev: |
|---|
| 1076 | if tlev[-1] != tag: |
|---|
| 1077 | # type of list is changed (ul<=>ol): |
|---|
| 1078 | for i in range(ltags.count(lent)): |
|---|
| 1079 | ltags.pop() |
|---|
| 1080 | out.append(etags.pop()) |
|---|
| 1081 | tlev[-1] = tag |
|---|
| 1082 | out.append('<' + tag + '>' + pp) |
|---|
| 1083 | etags.append('</' + tag + '>' + pp) |
|---|
| 1084 | ltags.append(lev) |
|---|
| 1085 | else: |
|---|
| 1086 | if ltags.count(lev) > 1: |
|---|
| 1087 | out.append(etags.pop()) |
|---|
| 1088 | ltags.pop() |
|---|
| 1089 | mtag = 'l' |
|---|
| 1090 | out.append('<li>') |
|---|
| 1091 | etags.append('</li>' + pp) |
|---|
| 1092 | ltags.append(lev) |
|---|
| 1093 | if s[:1] == '-': |
|---|
| 1094 | (s, mtag, lineno) = parse_table_or_blockquote(s, mtag, lineno) |
|---|
| 1095 | if p and mtag == 'l': |
|---|
| 1096 | (lev, mtag, lineno) = parse_point(t, s, lev, '', lineno) |
|---|
| 1097 | else: |
|---|
| 1098 | out.append(s) |
|---|
| 1099 | |
|---|
| 1100 | return (lev, mtag, lineno) |
|---|
| 1101 | |
|---|
| 1102 | def parse_point(t, s, lev, mtag, lineno): |
|---|
| 1103 | """ paragraphs in lists """ |
|---|
| 1104 | lent = len(t) |
|---|
| 1105 | if lent > lev: |
|---|
| 1106 | return parse_list(t, '.', s, 'ul', lev, mtag, lineno) |
|---|
| 1107 | elif lent < lev: |
|---|
| 1108 | while ltags[-1] > lent: |
|---|
| 1109 | ltags.pop() |
|---|
| 1110 | out.append(etags.pop()) |
|---|
| 1111 | lev = lent |
|---|
| 1112 | tlev[lev:] = [] |
|---|
| 1113 | mtag = '' |
|---|
| 1114 | elif lent == lev: |
|---|
| 1115 | if pend and mtag == '.': |
|---|
| 1116 | out.append(etags.pop()) |
|---|
| 1117 | ltags.pop() |
|---|
| 1118 | if br and mtag in ('l', '.'): |
|---|
| 1119 | out.append(br) |
|---|
| 1120 | if s == META: |
|---|
| 1121 | mtag = '' |
|---|
| 1122 | else: |
|---|
| 1123 | mtag = '.' |
|---|
| 1124 | if s[:1] == '-': |
|---|
| 1125 | (s, mtag, lineno) = parse_table_or_blockquote(s, mtag, lineno) |
|---|
| 1126 | if mtag == '.': |
|---|
| 1127 | out.append(pbeg) |
|---|
| 1128 | if pend: |
|---|
| 1129 | etags.append(pend) |
|---|
| 1130 | ltags.append(lev) |
|---|
| 1131 | out.append(s) |
|---|
| 1132 | return (lev, mtag, lineno) |
|---|
| 1133 | |
|---|
| 1134 | def parse_table_or_blockquote(s, mtag, lineno): |
|---|
| 1135 | # check next line. If next line : |
|---|
| 1136 | # - is empty -> this is an <hr /> tag |
|---|
| 1137 | # - consists '|' -> table |
|---|
| 1138 | # - consists other characters -> blockquote |
|---|
| 1139 | if (lineno + 1 >= strings_len or |
|---|
| 1140 | not (s.count('-') == len(s) and len(s) > 3)): |
|---|
| 1141 | return (s, mtag, lineno) |
|---|
| 1142 | |
|---|
| 1143 | lineno += 1 |
|---|
| 1144 | s = strings[lineno].strip() |
|---|
| 1145 | if s: |
|---|
| 1146 | if '|' in s: |
|---|
| 1147 | # table |
|---|
| 1148 | tout = [] |
|---|
| 1149 | thead = [] |
|---|
| 1150 | tbody = [] |
|---|
| 1151 | rownum = 0 |
|---|
| 1152 | t_id = '' |
|---|
| 1153 | t_cls = '' |
|---|
| 1154 | |
|---|
| 1155 | # parse table: |
|---|
| 1156 | while lineno < strings_len: |
|---|
| 1157 | s = strings[lineno].strip() |
|---|
| 1158 | if s[:1] == '=': |
|---|
| 1159 | # header or footer |
|---|
| 1160 | if s.count('=') == len(s) and len(s) > 3: |
|---|
| 1161 | if not thead: # if thead list is empty: |
|---|
| 1162 | thead = tout |
|---|
| 1163 | else: |
|---|
| 1164 | tbody.extend(tout) |
|---|
| 1165 | tout = [] |
|---|
| 1166 | rownum = 0 |
|---|
| 1167 | lineno += 1 |
|---|
| 1168 | continue |
|---|
| 1169 | |
|---|
| 1170 | m = regex_tq.match(s) |
|---|
| 1171 | if m: |
|---|
| 1172 | t_cls = m.group('c') or '' |
|---|
| 1173 | t_id = m.group('p') or '' |
|---|
| 1174 | break |
|---|
| 1175 | |
|---|
| 1176 | if rownum % 2: |
|---|
| 1177 | tr = '<tr class="even">' |
|---|
| 1178 | else: |
|---|
| 1179 | tr = '<tr class="first">' if rownum == 0 else '<tr>' |
|---|
| 1180 | tout.append(tr + ''.join(['<td%s>%s</td>' % ( |
|---|
| 1181 | ' class="num"' |
|---|
| 1182 | if regex_num.match(f) else '', |
|---|
| 1183 | f.strip() |
|---|
| 1184 | ) for f in s.split('|')]) + '</tr>' + pp) |
|---|
| 1185 | rownum += 1 |
|---|
| 1186 | lineno += 1 |
|---|
| 1187 | |
|---|
| 1188 | t_cls = ' class="%s%s"' % (class_prefix, t_cls) \ |
|---|
| 1189 | if t_cls and t_cls != 'id' else '' |
|---|
| 1190 | t_id = ' id="%s%s"' % (id_prefix, t_id) if t_id else '' |
|---|
| 1191 | s = '' |
|---|
| 1192 | if thead: |
|---|
| 1193 | s += '<thead>' + pp + ''.join([l for l in thead]) + '</thead>' + pp |
|---|
| 1194 | if not tbody: # tbody strings are in tout list |
|---|
| 1195 | tbody = tout |
|---|
| 1196 | tout = [] |
|---|
| 1197 | if tbody: # if tbody list is not empty: |
|---|
| 1198 | s += '<tbody>' + pp + ''.join([l for l in tbody]) + '</tbody>' + pp |
|---|
| 1199 | if tout: # tfoot is not empty: |
|---|
| 1200 | s += '<tfoot>' + pp + ''.join([l for l in tout]) + '</tfoot>' + pp |
|---|
| 1201 | s = '<table%s%s>%s%s</table>%s' % (t_cls, t_id, pp, s, pp) |
|---|
| 1202 | mtag = 't' |
|---|
| 1203 | else: |
|---|
| 1204 | # parse blockquote: |
|---|
| 1205 | bq_begin = lineno |
|---|
| 1206 | t_mode = False # embedded table |
|---|
| 1207 | t_cls = '' |
|---|
| 1208 | t_id = '' |
|---|
| 1209 | |
|---|
| 1210 | # search blockquote closing line: |
|---|
| 1211 | while lineno < strings_len: |
|---|
| 1212 | s = strings[lineno].strip() |
|---|
| 1213 | if not t_mode: |
|---|
| 1214 | m = regex_tq.match(s) |
|---|
| 1215 | if m: |
|---|
| 1216 | if (lineno + 1 == strings_len or |
|---|
| 1217 | '|' not in strings[lineno + 1]): |
|---|
| 1218 | t_cls = m.group('c') or '' |
|---|
| 1219 | t_id = m.group('p') or '' |
|---|
| 1220 | break |
|---|
| 1221 | |
|---|
| 1222 | if regex_bq_headline.match(s): |
|---|
| 1223 | if (lineno + 1 < strings_len and |
|---|
| 1224 | strings[lineno + 1].strip()): |
|---|
| 1225 | t_mode = True |
|---|
| 1226 | lineno += 1 |
|---|
| 1227 | continue |
|---|
| 1228 | elif regex_tq.match(s): |
|---|
| 1229 | t_mode = False |
|---|
| 1230 | lineno += 1 |
|---|
| 1231 | continue |
|---|
| 1232 | |
|---|
| 1233 | lineno += 1 |
|---|
| 1234 | |
|---|
| 1235 | t_cls = ' class="%s%s"' % (class_prefix, t_cls) \ |
|---|
| 1236 | if t_cls and t_cls != 'id' else '' |
|---|
| 1237 | t_id = ' id="%s%s"' % (id_prefix, t_id) \ |
|---|
| 1238 | if t_id else '' |
|---|
| 1239 | |
|---|
| 1240 | s = '<blockquote%s%s>%s</blockquote>%s' \ |
|---|
| 1241 | % (t_cls, |
|---|
| 1242 | t_id, |
|---|
| 1243 | render('\n'.join(strings[bq_begin:lineno])), pp) |
|---|
| 1244 | mtag = 'q' |
|---|
| 1245 | else: |
|---|
| 1246 | s = '<hr />' |
|---|
| 1247 | lineno -= 1 |
|---|
| 1248 | mtag = 'q' |
|---|
| 1249 | return (s, 'q', lineno) |
|---|
| 1250 | |
|---|
| 1251 | if sep == 'p': |
|---|
| 1252 | pbeg = "<p>" |
|---|
| 1253 | pend = "</p>" + pp |
|---|
| 1254 | br = '' |
|---|
| 1255 | else: |
|---|
| 1256 | pbeg = pend = '' |
|---|
| 1257 | br = "<br />" + pp if sep == 'br' else '' |
|---|
| 1258 | |
|---|
| 1259 | lev = 0 # nesting level of lists |
|---|
| 1260 | c0 = '' # first character of current line |
|---|
| 1261 | out = [] # list of processed lines |
|---|
| 1262 | etags = [] # trailing tags |
|---|
| 1263 | ltags = [] # level# correspondent to trailing tag |
|---|
| 1264 | tlev = [] # list of tags for each level ('ul' or 'ol') |
|---|
| 1265 | mtag = '' # marked tag (~last tag) ('l','.','h','p','t'). Used to set <br/> |
|---|
| 1266 | # and to avoid <p></p> around tables and blockquotes |
|---|
| 1267 | lineno = 0 |
|---|
| 1268 | strings_len = len(strings) |
|---|
| 1269 | while lineno < strings_len: |
|---|
| 1270 | s0 = strings[lineno][:1] |
|---|
| 1271 | s = strings[lineno].strip() |
|---|
| 1272 | """ # + - . --------------------- |
|---|
| 1273 | ## ++ -- .. ------- field | field | field <-title |
|---|
| 1274 | ### +++ --- ... quote ===================== |
|---|
| 1275 | #### ++++ ---- .... ------- field | field | field <-body |
|---|
| 1276 | ##### +++++ ----- ..... ---------------------:class[id] |
|---|
| 1277 | """ |
|---|
| 1278 | pc0 = c0 # first character of previous line |
|---|
| 1279 | c0 = s[:1] |
|---|
| 1280 | if c0: # for non empty strings |
|---|
| 1281 | if c0 in "#+-.": # first character is one of: # + - . |
|---|
| 1282 | (t1, t2, p, ss) = regex_list.findall(s)[0] |
|---|
| 1283 | # t1 - tag ("###") |
|---|
| 1284 | # t2 - tag ("+++", "---", "...") |
|---|
| 1285 | # p - paragraph point ('.')->for "++." or "--." |
|---|
| 1286 | # ss - other part of string |
|---|
| 1287 | if t1 or t2: |
|---|
| 1288 | # headers and lists: |
|---|
| 1289 | if c0 == '#': # headers |
|---|
| 1290 | (lev, mtag) = parse_title(t1, ss) |
|---|
| 1291 | lineno += 1 |
|---|
| 1292 | continue |
|---|
| 1293 | elif c0 == '+': # ordered list |
|---|
| 1294 | (lev, mtag, lineno) = parse_list(t2, p, ss, 'ol', lev, mtag, lineno) |
|---|
| 1295 | lineno += 1 |
|---|
| 1296 | continue |
|---|
| 1297 | elif c0 == '-': # unordered list, table or blockquote |
|---|
| 1298 | if p or ss: |
|---|
| 1299 | (lev, mtag, lineno) = parse_list(t2, p, ss, 'ul', lev, mtag, lineno) |
|---|
| 1300 | lineno += 1 |
|---|
| 1301 | continue |
|---|
| 1302 | else: |
|---|
| 1303 | (s, mtag, lineno) = parse_table_or_blockquote(s, mtag, lineno) |
|---|
| 1304 | elif lev > 0: # and c0 == '.' # paragraph in lists |
|---|
| 1305 | (lev, mtag, lineno) = parse_point(t2, ss, lev, mtag, lineno) |
|---|
| 1306 | lineno += 1 |
|---|
| 1307 | continue |
|---|
| 1308 | |
|---|
| 1309 | if lev == 0 and (mtag == 'q' or s == META): |
|---|
| 1310 | # new paragraph |
|---|
| 1311 | pc0 = '' |
|---|
| 1312 | |
|---|
| 1313 | if pc0 == '' or (mtag != 'p' and s0 not in (' ', '\t')): |
|---|
| 1314 | # paragraph |
|---|
| 1315 | out.extend(etags[::-1]) |
|---|
| 1316 | etags = [] |
|---|
| 1317 | ltags = [] |
|---|
| 1318 | tlev = [] |
|---|
| 1319 | lev = 0 |
|---|
| 1320 | if br and mtag == 'p': |
|---|
| 1321 | out.append(br) |
|---|
| 1322 | if mtag != 'q' and s != META: |
|---|
| 1323 | if pend: |
|---|
| 1324 | etags = [pend] |
|---|
| 1325 | out.append(pbeg) |
|---|
| 1326 | mtag = 'p' |
|---|
| 1327 | else: |
|---|
| 1328 | mtag = '' |
|---|
| 1329 | out.append(s) |
|---|
| 1330 | else: |
|---|
| 1331 | if lev > 0 and mtag == '.' and s == META: |
|---|
| 1332 | out.append(etags.pop()) |
|---|
| 1333 | ltags.pop() |
|---|
| 1334 | out.append(s) |
|---|
| 1335 | mtag = '' |
|---|
| 1336 | else: |
|---|
| 1337 | out.append(' ' + s) |
|---|
| 1338 | lineno += 1 |
|---|
| 1339 | out.extend(etags[::-1]) |
|---|
| 1340 | text = ''.join(out) |
|---|
| 1341 | |
|---|
| 1342 | ############################################################# |
|---|
| 1343 | # do strong,em,del |
|---|
| 1344 | ############################################################# |
|---|
| 1345 | text = regex_strong.sub('<strong>\g<t></strong>', text) |
|---|
| 1346 | text = regex_del.sub('<del>\g<t></del>', text) |
|---|
| 1347 | text = regex_em.sub('<em>\g<t></em>', text) |
|---|
| 1348 | |
|---|
| 1349 | ############################################################# |
|---|
| 1350 | # deal with images, videos, audios and links |
|---|
| 1351 | ############################################################# |
|---|
| 1352 | def sub_media(m): |
|---|
| 1353 | t, a, k, p, w = m.group('t', 'a', 'k', 'p', 'w') |
|---|
| 1354 | if not k: |
|---|
| 1355 | return m.group(0) |
|---|
| 1356 | k = local_html_escape(k) |
|---|
| 1357 | t = t or '' |
|---|
| 1358 | style = 'width:%s' % w if w else '' |
|---|
| 1359 | title = ' title="%s"' % local_html_escape(a).replace(META, DISABLED_META) if a else '' |
|---|
| 1360 | p_begin = p_end = '' |
|---|
| 1361 | if p == 'center': |
|---|
| 1362 | p_begin = '<p style="text-align:center">' |
|---|
| 1363 | p_end = '</p>' + pp |
|---|
| 1364 | elif p == 'blockleft': |
|---|
| 1365 | p_begin = '<p style="text-align:left">' |
|---|
| 1366 | p_end = '</p>' + pp |
|---|
| 1367 | elif p == 'blockright': |
|---|
| 1368 | p_begin = '<p style="text-align:right">' |
|---|
| 1369 | p_end = '</p>' + pp |
|---|
| 1370 | elif p in ('left', 'right'): |
|---|
| 1371 | style = ('float:%s' % p) + (';%s' % style if style else '') |
|---|
| 1372 | if t and regex_auto.match(t): |
|---|
| 1373 | p_begin = p_begin + '<a href="%s">' % t |
|---|
| 1374 | p_end = '</a>' + p_end |
|---|
| 1375 | t = '' |
|---|
| 1376 | if style: |
|---|
| 1377 | style = ' style="%s"' % style |
|---|
| 1378 | if p in ('video', 'audio'): |
|---|
| 1379 | t = render(t, {}, {}, 'br', URL, environment, latex, |
|---|
| 1380 | autolinks, protolinks, class_prefix, id_prefix, pretty_print) |
|---|
| 1381 | return '<%(p)s controls="controls"%(title)s%(style)s><source src="%(k)s" />%(t)s</%(p)s>' \ |
|---|
| 1382 | % dict(p=p, title=title, style=style, k=k, t=t) |
|---|
| 1383 | alt = ' alt="%s"' % local_html_escape(t).replace(META, DISABLED_META) if t else '' |
|---|
| 1384 | return '%(begin)s<img src="%(k)s"%(alt)s%(title)s%(style)s />%(end)s' \ |
|---|
| 1385 | % dict(begin=p_begin, k=k, alt=alt, title=title, style=style, end=p_end) |
|---|
| 1386 | |
|---|
| 1387 | def sub_link(m): |
|---|
| 1388 | t, a, k, p = m.group('t', 'a', 'k', 'p') |
|---|
| 1389 | if not k and not t: |
|---|
| 1390 | return m.group(0) |
|---|
| 1391 | t = t or '' |
|---|
| 1392 | a = local_html_escape(a) if a else '' |
|---|
| 1393 | if k: |
|---|
| 1394 | if '#' in k and ':' not in k.split('#')[0]: |
|---|
| 1395 | # wikipage, not external url |
|---|
| 1396 | k = k.replace('#', '#' + id_prefix) |
|---|
| 1397 | k = local_html_escape(k) |
|---|
| 1398 | title = ' title="%s"' % a.replace(META, DISABLED_META) if a else '' |
|---|
| 1399 | target = ' target="_blank"' if p == 'popup' else '' |
|---|
| 1400 | t = render(t, {}, {}, 'br', URL, environment, latex, None, |
|---|
| 1401 | None, class_prefix, id_prefix, pretty_print) if t else k |
|---|
| 1402 | return '<a href="%(k)s"%(title)s%(target)s>%(t)s</a>' \ |
|---|
| 1403 | % dict(k=k, title=title, target=target, t=t) |
|---|
| 1404 | if t == 'NEWLINE' and not a: |
|---|
| 1405 | return '<br />' + pp |
|---|
| 1406 | return '<span class="anchor" id="%s">%s</span>' % ( |
|---|
| 1407 | local_html_escape(id_prefix + t), |
|---|
| 1408 | render(a, {}, {}, 'br', URL, |
|---|
| 1409 | environment, latex, autolinks, |
|---|
| 1410 | protolinks, class_prefix, |
|---|
| 1411 | id_prefix, pretty_print)) |
|---|
| 1412 | |
|---|
| 1413 | parts = text.split(LINK) |
|---|
| 1414 | text = parts[0] |
|---|
| 1415 | for i, s in enumerate(links): |
|---|
| 1416 | if s is None: |
|---|
| 1417 | html = LINK |
|---|
| 1418 | else: |
|---|
| 1419 | html = regex_media_level2.sub(sub_media, s) |
|---|
| 1420 | if html == s: |
|---|
| 1421 | html = regex_link_level2.sub(sub_link, html) |
|---|
| 1422 | if html == s: |
|---|
| 1423 | # return unprocessed string as a signal of an error |
|---|
| 1424 | html = '[[%s]]' % s |
|---|
| 1425 | text += html + parts[i + 1] |
|---|
| 1426 | |
|---|
| 1427 | ############################################################# |
|---|
| 1428 | # process all code text |
|---|
| 1429 | ############################################################# |
|---|
| 1430 | def expand_meta(m): |
|---|
| 1431 | code, b, p, s = segments.pop(0) |
|---|
| 1432 | if code is None or m.group() == DISABLED_META: |
|---|
| 1433 | return local_html_escape(s) |
|---|
| 1434 | if b in extra: |
|---|
| 1435 | if code[:1] == '\n': |
|---|
| 1436 | code = code[1:] |
|---|
| 1437 | if code[-1:] == '\n': |
|---|
| 1438 | code = code[:-1] |
|---|
| 1439 | if p: |
|---|
| 1440 | return str(extra[b](code, p)) |
|---|
| 1441 | else: |
|---|
| 1442 | return str(extra[b](code)) |
|---|
| 1443 | elif b == 'cite': |
|---|
| 1444 | return '[' + ','.join('<a href="#%s" class="%s">%s</a>' % |
|---|
| 1445 | (id_prefix + d, b, d) for d in local_html_escape(code).split(',')) + ']' |
|---|
| 1446 | elif b == 'latex': |
|---|
| 1447 | return LATEX % urllib_quote(code) |
|---|
| 1448 | elif b in html_colors: |
|---|
| 1449 | return '<span style="color: %s">%s</span>' \ |
|---|
| 1450 | % (b, render(code, {}, {}, 'br', URL, environment, latex, |
|---|
| 1451 | autolinks, protolinks, class_prefix, id_prefix, pretty_print)) |
|---|
| 1452 | elif b in ('c', 'color') and p: |
|---|
| 1453 | c = p.split(':') |
|---|
| 1454 | fg = 'color: %s;' % c[0] if c[0] else '' |
|---|
| 1455 | bg = 'background-color: %s;' % c[1] if len(c) > 1 and c[1] else '' |
|---|
| 1456 | return '<span style="%s%s">%s</span>' \ |
|---|
| 1457 | % (fg, bg, render(code, {}, {}, 'br', URL, environment, latex, |
|---|
| 1458 | autolinks, protolinks, class_prefix, id_prefix, pretty_print)) |
|---|
| 1459 | cls = ' class="%s%s"' % (class_prefix, b) if b and b != 'id' else '' |
|---|
| 1460 | id = ' id="%s%s"' % (id_prefix, local_html_escape(p)) if p else '' |
|---|
| 1461 | beg = (code[:1] == '\n') |
|---|
| 1462 | end = [None, -1][code[-1:] == '\n'] |
|---|
| 1463 | if beg and end: |
|---|
| 1464 | return '<pre><code%s%s>%s</code></pre>%s' % (cls, id, local_html_escape(code[1:-1]), pp) |
|---|
| 1465 | return '<code%s%s>%s</code>' % (cls, id, local_html_escape(code[beg:end])) |
|---|
| 1466 | |
|---|
| 1467 | text = regex_expand_meta.sub(expand_meta, text) |
|---|
| 1468 | |
|---|
| 1469 | if environment: |
|---|
| 1470 | text = replace_components(text, environment) |
|---|
| 1471 | |
|---|
| 1472 | return text.translate(ttab_out) |
|---|
| 1473 | |
|---|
| 1474 | |
|---|
| 1475 | def markmin2html(text, extra={}, allowed={}, sep='p', |
|---|
| 1476 | autolinks='default', protolinks='default', |
|---|
| 1477 | class_prefix='', id_prefix='markmin_', pretty_print=False): |
|---|
| 1478 | return render(text, extra, allowed, sep, |
|---|
| 1479 | autolinks=autolinks, protolinks=protolinks, |
|---|
| 1480 | class_prefix=class_prefix, id_prefix=id_prefix, |
|---|
| 1481 | pretty_print=pretty_print) |
|---|
| 1482 | |
|---|
| 1483 | |
|---|
| 1484 | def run_doctests(): |
|---|
| 1485 | import doctest |
|---|
| 1486 | doctest.testmod() |
|---|
| 1487 | |
|---|
| 1488 | |
|---|
| 1489 | if __name__ == '__main__': |
|---|
| 1490 | import sys |
|---|
| 1491 | import doctest |
|---|
| 1492 | from textwrap import dedent |
|---|
| 1493 | |
|---|
| 1494 | html = dedent(""" |
|---|
| 1495 | <!doctype html> |
|---|
| 1496 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> |
|---|
| 1497 | <head> |
|---|
| 1498 | <meta http-equiv="content-type" content="text/html; charset=utf-8" /> |
|---|
| 1499 | %(style)s |
|---|
| 1500 | <title>%(title)s</title> |
|---|
| 1501 | </head> |
|---|
| 1502 | <body> |
|---|
| 1503 | %(body)s |
|---|
| 1504 | </body> |
|---|
| 1505 | </html>""")[1:] |
|---|
| 1506 | |
|---|
| 1507 | if sys.argv[1:2] == ['-h']: |
|---|
| 1508 | style = dedent(""" |
|---|
| 1509 | <style> |
|---|
| 1510 | blockquote { background-color: #FFFAAE; padding: 7px; } |
|---|
| 1511 | table { border-collapse: collapse; } |
|---|
| 1512 | thead td { border-bottom: 1px solid; } |
|---|
| 1513 | tfoot td { border-top: 1px solid; } |
|---|
| 1514 | .tableclass1 { background-color: lime; } |
|---|
| 1515 | .tableclass1 thead { color: yellow; background-color: green; } |
|---|
| 1516 | .tableclass1 tfoot { color: yellow; background-color: green; } |
|---|
| 1517 | .tableclass1 .even td { background-color: #80FF7F; } |
|---|
| 1518 | .tableclass1 .first td {border-top: 1px solid; } |
|---|
| 1519 | |
|---|
| 1520 | td.num { text-align: right; } |
|---|
| 1521 | pre { background-color: #E0E0E0; padding: 5px; } |
|---|
| 1522 | </style>""")[1:] |
|---|
| 1523 | |
|---|
| 1524 | print(html % dict(title="Markmin markup language", |
|---|
| 1525 | style=style, |
|---|
| 1526 | body=markmin2html(__doc__, pretty_print=True))) |
|---|
| 1527 | elif sys.argv[1:2] == ['-t']: |
|---|
| 1528 | from timeit import Timer |
|---|
| 1529 | |
|---|
| 1530 | loops = 1000 |
|---|
| 1531 | ts = Timer("markmin2html(__doc__)", "from markmin2html import markmin2html") |
|---|
| 1532 | print('timeit "markmin2html(__doc__)":') |
|---|
| 1533 | t = min([ts.timeit(loops) for i in range(3)]) |
|---|
| 1534 | print("%s loops, best of 3: %.3f ms per loop" % (loops, t / 1000 * loops)) |
|---|
| 1535 | elif len(sys.argv) > 1: |
|---|
| 1536 | fargv = open(sys.argv[1], 'r') |
|---|
| 1537 | try: |
|---|
| 1538 | markmin_text = fargv.read() |
|---|
| 1539 | |
|---|
| 1540 | # embed css file from second parameter into html file |
|---|
| 1541 | if len(sys.argv) > 2: |
|---|
| 1542 | if sys.argv[2].startswith('@'): |
|---|
| 1543 | markmin_style = '<link rel="stylesheet" href="' + sys.argv[2][1:] + '"/>' |
|---|
| 1544 | else: |
|---|
| 1545 | fargv2 = open(sys.argv[2], 'r') |
|---|
| 1546 | try: |
|---|
| 1547 | markmin_style = "<style>\n" + fargv2.read() + "</style>" |
|---|
| 1548 | finally: |
|---|
| 1549 | fargv2.close() |
|---|
| 1550 | else: |
|---|
| 1551 | markmin_style = "" |
|---|
| 1552 | |
|---|
| 1553 | print(html % dict(title=sys.argv[1], style=markmin_style, |
|---|
| 1554 | body=markmin2html(markmin_text, pretty_print=True))) |
|---|
| 1555 | finally: |
|---|
| 1556 | fargv.close() |
|---|
| 1557 | |
|---|
| 1558 | else: |
|---|
| 1559 | print("Usage: " + sys.argv[0] + " -h | -t | file.markmin [file.css|@path_to/css]") |
|---|
| 1560 | print("where: -h - print __doc__") |
|---|
| 1561 | print(" -t - timeit __doc__ (for testing purpuse only)") |
|---|
| 1562 | print(" file.markmin [file.css] - process file.markmin + built in file.css (optional)") |
|---|
| 1563 | print(" file.markmin [@path_to/css] - process file.markmin + link path_to/css (optional)") |
|---|
| 1564 | run_doctests() |
|---|
