summaryrefslogtreecommitdiff
path: root/pycco/main.py
blob: 09584b3cee2f9bd4a693236d49724e8bc24377ad (plain)
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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
#!/usr/bin/env python

"""
"**Pycco**" is a Python port of [Docco](http://jashkenas.github.com/docco/):
the original quick-and-dirty, hundred-line-long, literate-programming-style
documentation generator. It produces HTML that displays your comments
alongside your code. Comments are passed through
[Markdown](http://daringfireball.net/projects/markdown/syntax) and
[SmartyPants](http://daringfireball.net/projects/smartypants), while code is
passed through [Pygments](http://pygments.org/) for syntax highlighting.
This page is the result of running Pycco against its own source file.

If you install Pycco, you can run it from the command-line:

    pycco src/*.py

This will generate linked HTML documentation for the named source files,
saving it into a `docs` folder by default.

The [source for Pycco](https://github.com/fitzgen/pycco) is available on GitHub,
and released under the MIT license.

To install Pycco, simply

    pip install pycco

Or, to install the latest source

    git clone git://github.com/fitzgen/pycco.git
    cd pycco
    python setup.py install
"""

# === Main Documentation Generation Functions ===

def generate_documentation(source, outdir=None, preserve_paths=True,
                           language=None):
    """
    Generate the documentation for a source file by reading it in, splitting it
    up into comment/code sections, highlighting them for the appropriate
    language, and merging them into an HTML template.
    """

    if not outdir:
        raise TypeError("Missing the required 'outdir' keyword argument.")
    code = open(source, "r").read()
    language = get_language(source, code, language=language)
    sections = parse(source, code, language)
    highlight(source, sections, language, preserve_paths=preserve_paths, outdir=outdir)
    return generate_html(source, sections, preserve_paths=preserve_paths, outdir=outdir)

def parse(source, code, language):
    """
    Given a string of source code, parse out each comment and the code that
    follows it, and create an individual **section** for it.
    Sections take the form:

        { "docs_text": ...,
          "docs_html": ...,
          "code_text": ...,
          "code_html": ...,
          "num":       ...
        }
    """

    lines = code.split("\n")
    sections = []
    has_code = docs_text = code_text = ""

    if lines[0].startswith("#!"):
        lines.pop(0)

    if language["name"] == "python":
        for linenum, line in enumerate(lines[:2]):
            if re.search(r'coding[:=]\s*([-\w.]+)', lines[linenum]):
                lines.pop(linenum)
                break


    def save(docs, code):
        if docs or code:
            sections.append({
                "docs_text": docs,
                "code_text": code
            })

    # Setup the variables to get ready to check for multiline comments
    multi_line = False
    multi_line_delimiters = [language.get("multistart"), language.get("multiend")]

    for line in lines:

        # Only go into multiline comments section when one of the delimiters is
        # found to be at the start of a line
        if all(multi_line_delimiters) and any([line.lstrip().startswith(delim) or line.rstrip().endswith(delim) for delim in multi_line_delimiters]):
            if not multi_line:
                multi_line = True

            else:
                multi_line = False

            if (multi_line
               and line.strip().endswith(language.get("multiend"))
               and len(line.strip()) > len(language.get("multiend"))):
                multi_line = False

            # Get rid of the delimiters so that they aren't in the final docs
            line = line.replace(language["multistart"], '')
            line = line.replace(language["multiend"], '')
            docs_text += line.strip() + '\n'
            indent_level = re.match("\s*", line).group(0)

            if has_code and docs_text.strip():
                save(docs_text, code_text[:-1])
                code_text = code_text.split('\n')[-1]
                has_code = docs_text = ''

        elif multi_line:
            # Remove leading spaces
            if re.match(r' {%d}' % len(indent_level), line):
                docs_text += line[len(indent_level):] + '\n'
            else:
                docs_text += line + '\n'

        elif re.match(language["comment_matcher"], line):
            if has_code:
                save(docs_text, code_text)
                has_code = docs_text = code_text = ''
            docs_text += re.sub(language["comment_matcher"], "", line) + "\n"

        else:
            if code_text and any([line.lstrip().startswith(x) for x in ['class ', 'def ', '@']]):
                if not code_text.lstrip().startswith("@"):
                    save(docs_text, code_text)
                    code_text = has_code = docs_text = ''

            has_code = True
            code_text += line + '\n'


    save(docs_text, code_text)

    return sections

# === Preprocessing the comments ===

def preprocess(comment, section_nr, preserve_paths=True, outdir=None):
    """
    Add cross-references before having the text processed by markdown.  It's
    possible to reference another file, like this : `[[main.py]]` which renders
    [[main.py]]. You can also reference a specific section of another file, like
    this: `[[main.py#highlighting-the-source-code]]` which renders as
    [[main.py#highlighting-the-source-code]]. Sections have to be manually
    declared; they are written on a single line, and surrounded by equals signs:
    `=== like this ===`
    """

    if not outdir:
        raise TypeError("Missing the required 'outdir' keyword argument.")
    def sanitize_section_name(name):
        return "-".join(name.lower().strip().split(" "))

    def replace_crossref(match):
        # Check if the match contains an anchor
        if '#' in match.group(1):
            name, anchor = match.group(1).split('#')
            return " [%s](%s#%s)" % (name,
                                     path.basename(destination(name,
                                                               preserve_paths=preserve_paths,
                                                               outdir=outdir)),
                                     anchor)

        else:
            return " [%s](%s)" % (match.group(1),
                                  path.basename(destination(match.group(1),
                                                            preserve_paths=preserve_paths,
                                                            outdir=outdir)))

    def replace_section_name(match):
        return '%(lvl)s <span id="%(id)s" href="%(id)s">%(name)s</span>' % {
            "lvl"  : re.sub('=', '#', match.group(1)),
            "id"   : sanitize_section_name(match.group(2)),
            "name" : match.group(2)
        }

    comment = re.sub('^([=]+)([^=]+)[=]*\s*$', replace_section_name, comment)
    comment = re.sub('[^`]\[\[(.+?)\]\]', replace_crossref, comment)

    return comment

# === Highlighting the source code ===

def highlight(source, sections, language, preserve_paths=True, outdir=None):
    """
    Highlights a single chunk of code using the **Pygments** module, and runs
    the text of its corresponding comment through **Markdown**.

    We process the entire file in a single call to Pygments by inserting little
    marker comments between each section and then splitting the result string
    wherever our markers occur.
    """

    if not outdir:
        raise TypeError("Missing the required 'outdir' keyword argument.")

    output = pygments.highlight(language["divider_text"].join(section["code_text"].rstrip() for section in sections),
                                language["lexer"],
                                formatters.get_formatter_by_name("html"))

    output = output.replace(highlight_start, "").replace(highlight_end, "")
    fragments = re.split(language["divider_html"], output)
    for i, section in enumerate(sections):
        section["code_html"] = highlight_start + shift(fragments, "") + highlight_end
        try:
            docs_text = unicode(section["docs_text"])
        except UnicodeError:
            docs_text = unicode(section["docs_text"].decode('utf-8'))
        section["docs_html"] = markdown(preprocess(docs_text,
                                                   i,
                                                   preserve_paths=preserve_paths,
                                                   outdir=outdir))
        section["num"] = i

# === HTML Code generation ===

def generate_html(source, sections, preserve_paths=True, outdir=None):
    """
    Once all of the code is finished highlighting, we can generate the HTML file
    and write out the documentation. Pass the completed sections into the
    template found in `resources/pycco.html`.

    Pystache will attempt to recursively render context variables, so we must
    replace any occurences of `{{`, which is valid in some languages, with a
    "unique enough" identifier before rendering, and then post-process the
    rendered template and change the identifier back to `{{`.
    """

    if not outdir:
        raise TypeError("Missing the required 'outdir' keyword argument")
    title = path.basename(source)
    dest = destination(source, preserve_paths=preserve_paths, outdir=outdir)
    csspath = path.relpath(path.join(outdir, "pycco.css"), path.split(dest)[0])

    for sect in sections:
        sect["code_html"] = re.sub(r"\{\{", r"__DOUBLE_OPEN_STACHE__", sect["code_html"])

    rendered = pycco_template({
        "title"       : title,
        "stylesheet"  : csspath,
        "sections"    : sections,
        "source"      : source,
        "path"        : path,
        "destination" : destination
    })

    return re.sub(r"__DOUBLE_OPEN_STACHE__", "{{", rendered).encode("utf-8")

# === Helpers & Setup ===

# This module contains all of our static resources.
import pycco_resources

# Import our external dependencies.
import optparse
import os
import pygments
import pystache
import re
import sys
import time
from markdown import markdown
from os import path
from pygments import lexers, formatters

# A list of the languages that Pycco supports, mapping the file extension to
# the name of the Pygments lexer and the symbol that indicates a comment. To
# add another language to Pycco's repertoire, add it here.
languages = {
    ".coffee": { "name": "coffee-script", "symbol": "#",
        "multistart": '###', "multiend": '###' },

    ".pl":  { "name": "perl", "symbol": "#" },

    ".sql": { "name": "sql", "symbol": "--" },

    ".c":   { "name": "c", "symbol": "//",
        "multistart": "/*", "multiend": "*/"},

    ".cpp": { "name": "cpp", "symbol": "//"},

    ".js": { "name": "javascript", "symbol": "//",
        "multistart": "/*", "multiend": "*/"},

    ".rb": { "name": "ruby", "symbol": "#",
        "multistart": "=begin", "multiend": "=end"},

    ".py": { "name": "python", "symbol": "#",
        "multistart": '"""', "multiend": '"""' },

    ".scm": { "name": "scheme", "symbol": ";;",
        "multistart": "#|", "multiend": "|#"},

    ".lua": { "name": "lua", "symbol": "--",
        "multistart": "--[[", "multiend": "--]]"},

    ".erl": { "name": "erlang", "symbol": "%%" },

    ".tcl":  { "name": "tcl", "symbol": "#" },

    ".hs": { "name": "haskell", "symbol": "--",
        "multistart": "{-", "multiend": "-}"},
}

# Build out the appropriate matchers and delimiters for each language.
for ext, l in languages.items():
    # Does the line begin with a comment?
    l["comment_matcher"] = re.compile(r"^\s*" + l["symbol"] + "\s?")

    # The dividing token we feed into Pygments, to delimit the boundaries between
    # sections.
    l["divider_text"] = "\n" + l["symbol"] + "DIVIDER\n"

    # The mirror of `divider_text` that we expect Pygments to return. We can split
    # on this to recover the original sections.
    l["divider_html"] = re.compile(r'\n*<span class="c[1]?">' + l["symbol"] + 'DIVIDER</span>\n*')

    # Get the Pygments Lexer for this language.
    l["lexer"] = lexers.get_lexer_by_name(l["name"])

def get_language(source, code, language=None):
    """Get the current language we're documenting, based on the extension."""

    if language is not None:
        for l in languages.values():
            if l["name"] == language:
                return l
        else:
            raise ValueError("Unknown forced language: " + language)

    m = re.match(r'.*(\..+)', os.path.basename(source))
    if m and m.group(1) in languages:
        return languages[m.group(1)]
    else:
        lang = lexers.guess_lexer(code).name.lower()
        for l in languages.values():
            if l["name"] == lang:
                return l
        else:
            raise ValueError("Can't figure out the language!")

def destination(filepath, preserve_paths=True, outdir=None):
    """
    Compute the destination HTML path for an input source file path. If the
    source is `lib/example.py`, the HTML will be at `docs/example.html`
    """

    dirname, filename = path.split(filepath)
    if not outdir:
        raise TypeError("Missing the required 'outdir' keyword argument.")
    try:
        name = re.sub(r"\.[^.]*$", "", filename)
    except ValueError:
        name = filename
    if preserve_paths:
        name = path.join(dirname, name)
    return path.join(outdir, "%s.html" % name)

def shift(list, default):
    """
    Shift items off the front of the `list` until it is empty, then return
    `default`.
    """

    try:
        return list.pop(0)
    except IndexError:
        return default

def ensure_directory(directory):
    """Ensure that the destination directory exists."""

    if not os.path.isdir(directory):
        os.makedirs(directory)

def template(source):
    return lambda context: pystache.render(source, context)

# Create the template that we will use to generate the Pycco HTML page.
pycco_template = template(pycco_resources.html)

# The CSS styles we'd like to apply to the documentation.
pycco_styles = pycco_resources.css

# The start of each Pygments highlight block.
highlight_start = "<div class=\"highlight\"><pre>"

# The end of each Pygments highlight block.
highlight_end = "</pre></div>"

def process(sources, preserve_paths=True, outdir=None, language=None):
    """For each source file passed as argument, generate the documentation."""

    if not outdir:
        raise TypeError("Missing the required 'outdir' keyword argument.")

    # Make a copy of sources given on the command line. `main()` needs the
    # original list when monitoring for changed files.
    sources = sorted(sources)

    # Proceed to generating the documentation.
    if sources:
        ensure_directory(outdir)
        css = open(path.join(outdir, "pycco.css"), "w")
        css.write(pycco_styles)
        css.close()

        def next_file():
            s = sources.pop(0)
            dest = destination(s, preserve_paths=preserve_paths, outdir=outdir)

            try:
                os.makedirs(path.split(dest)[0])
            except OSError:
                pass

            with open(dest, "w") as f:
                f.write(generate_documentation(s, preserve_paths=preserve_paths, outdir=outdir,
                                               language=language))

            print "pycco = %s -> %s" % (s, dest)

            if sources:
                next_file()
        next_file()

__all__ = ("process", "generate_documentation")


def monitor(sources, opts):
    """Monitor each source file and re-generate documentation on change."""

    # The watchdog modules are imported in `main()` but we need to re-import
    # here to bring them into the local namespace.
    import watchdog.events
    import watchdog.observers

    # Watchdog operates on absolute paths, so map those to original paths
    # as specified on the command line.
    absolute_sources = dict((os.path.abspath(source), source)
                            for source in sources)

    class RegenerateHandler(watchdog.events.FileSystemEventHandler):
        """A handler for recompiling files which triggered watchdog events"""
        def on_modified(self, event):
            """Regenerate documentation for a file which triggered an event"""
            # Re-generate documentation from a source file if it was listed on
            # the command line. Watchdog monitors whole directories, so other
            # files may cause notifications as well.
            if event.src_path in absolute_sources:
                process([absolute_sources[event.src_path]],
                        outdir=opts.outdir,
                        preserve_paths=opts.paths)

    # Set up an observer which monitors all directories for files given on
    # the command line and notifies the handler defined above.
    event_handler = RegenerateHandler()
    observer = watchdog.observers.Observer()
    directories = set(os.path.split(source)[0] for source in sources)
    for directory in directories:
        observer.schedule(event_handler, path=directory)

    # Run the file change monitoring loop until the user hits Ctrl-C.
    observer.start()
    try:
        while True:
            time.sleep(1)
    except KeyboardInterrupt:
        observer.stop()
        observer.join()


def main():
    """Hook spot for the console script."""

    parser = optparse.OptionParser()
    parser.add_option('-p', '--paths', action='store_true',
                      help='Preserve path structure of original files')

    parser.add_option('-d', '--directory', action='store', type='string',
                      dest='outdir', default='docs',
                      help='The output directory that the rendered files should go to.')

    parser.add_option('-w', '--watch', action='store_true',
                      help='Watch original files and re-generate documentation on changes')

    parser.add_option('-l', '--force-language', action='store', type='string',
                      dest='language', default=None,
                      help='Force the language for the given files')
    opts, sources = parser.parse_args()

    process(sources, outdir=opts.outdir, preserve_paths=opts.paths,
            language=opts.language)

    # If the -w / --watch option was present, monitor the source directories
    # for changes and re-generate documentation for source files whenever they
    # are modified.
    if opts.watch:
        try:
            import watchdog.events
            import watchdog.observers
        except ImportError:
            sys.exit('The -w/--watch option requires the watchdog package.')

        monitor(sources, opts)

# Run the script.
if __name__ == "__main__":
    main()