Source

python-peps / pep2html.py

The default branch has multiple heads

  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
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
#!/usr/bin/env python
"""Convert PEPs to (X)HTML - courtesy of /F

Usage: %(PROGRAM)s [options] [<peps> ...]

Options:

-u, --user
    python.org username

-b, --browse
    After generating the HTML, direct your web browser to view it
    (using the Python webbrowser module).  If both -i and -b are
    given, this will browse the on-line HTML; otherwise it will
    browse the local HTML.  If no pep arguments are given, this
    will browse PEP 0.

-i, --install
    After generating the HTML, install it and the plaintext source file
    (.txt) on python.org.  In that case the user's name is used in the scp
    and ssh commands, unless "-u username" is given (in which case, it is
    used instead).  Without -i, -u is ignored.

-l, --local
    Same as -i/--install, except install on the local machine.  Use this
    when logged in to the python.org machine (dinsdale).

-q, --quiet
    Turn off verbose messages.

-h, --help
    Print this help message and exit.

The optional arguments ``peps`` are either pep numbers or .txt files.
"""

import sys
import os
import re
import cgi
import glob
import getopt
import errno
import random
import time

REQUIRES = {'python': '2.2',
            'docutils': '0.2.7'}
PROGRAM = sys.argv[0]
RFCURL = 'http://www.faqs.org/rfcs/rfc%d.html'
PEPURL = 'pep-%04d.html'
PEPCVSURL = ('http://hg.python.org/peps/file/tip/pep-%04d.txt')
PEPDIRRUL = 'http://www.python.org/peps/'


HOST = "dinsdale.python.org"                    # host for update
HDIR = "/data/ftp.python.org/pub/www.python.org/peps" # target host directory
LOCALVARS = "Local Variables:"

COMMENT = """<!--
This HTML is auto-generated.  DO NOT EDIT THIS FILE!  If you are writing a new
PEP, see http://www.python.org/peps/pep-0001.html for instructions and links
to templates.  DO NOT USE THIS HTML FILE AS YOUR TEMPLATE!
-->"""

# The generated HTML doesn't validate -- you cannot use <hr> and <h3> inside
# <pre> tags.  But if I change that, the result doesn't look very nice...
DTD = ('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"\n'
       '                      "http://www.w3.org/TR/REC-html40/loose.dtd">')

fixpat = re.compile("((https?|ftp):[-_a-zA-Z0-9/.+~:?#$=&,]+)|(pep-\d+(.txt)?)|"
                    "(RFC[- ]?(?P<rfcnum>\d+))|"
                    "(PEP\s+(?P<pepnum>\d+))|"
                    ".")

EMPTYSTRING = ''
SPACE = ' '
COMMASPACE = ', '



def usage(code, msg=''):
    """Print usage message and exit.  Uses stderr if code != 0."""
    if code == 0:
        out = sys.stdout
    else:
        out = sys.stderr
    print >> out, __doc__ % globals()
    if msg:
        print >> out, msg
    sys.exit(code)



def fixanchor(current, match):
    text = match.group(0)
    link = None
    if (text.startswith('http:') or text.startswith('https:')
        or text.startswith('ftp:')):
        # Strip off trailing punctuation.  Pattern taken from faqwiz.
        ltext = list(text)
        while ltext:
            c = ltext.pop()
            if c not in '();:,.?\'"<>':
                ltext.append(c)
                break
        link = EMPTYSTRING.join(ltext)
    elif text.startswith('pep-') and text <> current:
        link = os.path.splitext(text)[0] + ".html"
    elif text.startswith('PEP'):
        pepnum = int(match.group('pepnum'))
        link = PEPURL % pepnum
    elif text.startswith('RFC'):
        rfcnum = int(match.group('rfcnum'))
        link = RFCURL % rfcnum
    if link:
        return '<a href="%s">%s</a>' % (cgi.escape(link), cgi.escape(text))
    return cgi.escape(match.group(0)) # really slow, but it works...



NON_MASKED_EMAILS = [
    'peps@python.org',
    'python-list@python.org',
    'python-dev@python.org',
    ]

def fixemail(address, pepno):
    if address.lower() in NON_MASKED_EMAILS:
        # return hyperlinked version of email address
        return linkemail(address, pepno)
    else:
        # return masked version of email address
        parts = address.split('@', 1)
        return '%s&#32;&#97;t&#32;%s' % (parts[0], parts[1])


def linkemail(address, pepno):
    parts = address.split('@', 1)
    return ('<a href="mailto:%s&#64;%s?subject=PEP%%20%s">'
            '%s&#32;&#97;t&#32;%s</a>'
            % (parts[0], parts[1], pepno, parts[0], parts[1]))


def fixfile(inpath, input_lines, outfile):
    from email.Utils import parseaddr
    basename = os.path.basename(inpath)
    infile = iter(input_lines)
    # convert plaintext pep to minimal XHTML markup
    print >> outfile, DTD
    print >> outfile, '<html>'
    print >> outfile, COMMENT
    print >> outfile, '<head>'
    # head
    header = []
    pep = ""
    title = ""
    for line in infile:
        if not line.strip():
            break
        if line[0].strip():
            if ":" not in line:
                break
            key, value = line.split(":", 1)
            value = value.strip()
            header.append((key, value))
        else:
            # continuation line
            key, value = header[-1]
            value = value + line
            header[-1] = key, value
        if key.lower() == "title":
            title = value
        elif key.lower() == "pep":
            pep = value
    if pep:
        title = "PEP " + pep + " -- " + title
    if title:
        print >> outfile, '  <title>%s</title>' % cgi.escape(title)
    r = random.choice(range(64))
    print >> outfile, (
        '  <link rel="STYLESHEET" href="style.css" type="text/css" />\n'
        '</head>\n'
        '<body bgcolor="white">\n'
        '<table class="navigation" cellpadding="0" cellspacing="0"\n'
        '       width="100%%" border="0">\n'
        '<tr><td class="navicon" width="150" height="35">\n'
        '<a href="../" title="Python Home Page">\n'
        '<img src="../pics/PyBanner%03d.gif" alt="[Python]"\n'
        ' border="0" width="150" height="35" /></a></td>\n'
        '<td class="textlinks" align="left">\n'
        '[<b><a href="../">Python Home</a></b>]' % r)
    if basename <> 'pep-0000.txt':
        print >> outfile, '[<b><a href=".">PEP Index</a></b>]'
    if pep:
        try:
            print >> outfile, ('[<b><a href="pep-%04d.txt">PEP Source</a>'
                               '</b>]' % int(pep))
        except ValueError, error:
            print >> sys.stderr, ('ValueError (invalid PEP number): %s'
                                  % error)
    print >> outfile, '</td></tr></table>'
    print >> outfile, '<div class="header">\n<table border="0">'
    for k, v in header:
        if k.lower() in ('author', 'discussions-to'):
            mailtos = []
            for part in re.split(',\s*', v):
                if '@' in part:
                    realname, addr = parseaddr(part)
                    if k.lower() == 'discussions-to':
                        m = linkemail(addr, pep)
                    else:
                        m = fixemail(addr, pep)
                    mailtos.append('%s &lt;%s&gt;' % (realname, m))
                elif part.startswith('http:'):
                    mailtos.append(
                        '<a href="%s">%s</a>' % (part, part))
                else:
                    mailtos.append(part)
            v = COMMASPACE.join(mailtos)
        elif k.lower() in ('replaces', 'replaced-by', 'requires'):
            otherpeps = ''
            for otherpep in re.split(',?\s+', v):
                otherpep = int(otherpep)
                otherpeps += '<a href="pep-%04d.html">%i</a> ' % (otherpep,
                                                                  otherpep)
            v = otherpeps
        elif k.lower() in ('last-modified',):
            date = v or time.strftime('%d-%b-%Y',
                                      time.localtime(os.stat(inpath)[8]))
            try:
                url = PEPCVSURL % int(pep)
                v = '<a href="%s">%s</a> ' % (url, cgi.escape(date))
            except ValueError, error:
                v = date
        elif k.lower() in ('content-type',):
            url = PEPURL % 9
            pep_type = v or 'text/plain'
            v = '<a href="%s">%s</a> ' % (url, cgi.escape(pep_type))
        else:
            v = cgi.escape(v)
        print >> outfile, '  <tr><th>%s:&nbsp;</th><td>%s</td></tr>' \
              % (cgi.escape(k), v)
    print >> outfile, '</table>'
    print >> outfile, '</div>'
    print >> outfile, '<hr />'
    print >> outfile, '<div class="content">'
    need_pre = 1
    for line in infile:
        if line[0] == '\f':
            continue
        if line.strip() == LOCALVARS:
            break
        if line[0].strip():
            if not need_pre:
                print >> outfile, '</pre>'
            print >> outfile, '<h3>%s</h3>' % line.strip()
            need_pre = 1
        elif not line.strip() and need_pre:
            continue
        else:
            # PEP 0 has some special treatment
            if basename == 'pep-0000.txt':
                parts = line.split()
                if len(parts) > 1 and re.match(r'\s*\d{1,4}', parts[1]):
                    # This is a PEP summary line, which we need to hyperlink
                    url = PEPURL % int(parts[1])
                    if need_pre:
                        print >> outfile, '<pre>'
                        need_pre = 0
                    print >> outfile, re.sub(
                        parts[1],
                        '<a href="%s">%s</a>' % (url, parts[1]),
                        line, 1),
                    continue
                elif parts and '@' in parts[-1]:
                    # This is a pep email address line, so filter it.
                    url = fixemail(parts[-1], pep)
                    if need_pre:
                        print >> outfile, '<pre>'
                        need_pre = 0
                    print >> outfile, re.sub(
                        parts[-1], url, line, 1),
                    continue
            line = fixpat.sub(lambda x, c=inpath: fixanchor(c, x), line)
            if need_pre:
                print >> outfile, '<pre>'
                need_pre = 0
            outfile.write(line)
    if not need_pre:
        print >> outfile, '</pre>'
    print >> outfile, '</div>'
    print >> outfile, '</body>'
    print >> outfile, '</html>'


docutils_settings = None
"""Runtime settings object used by Docutils.  Can be set by the client
application when this module is imported."""

def fix_rst_pep(inpath, input_lines, outfile):
    from docutils import core
    output = core.publish_string(
        source=''.join(input_lines),
        source_path=inpath,
        destination_path=outfile.name,
        reader_name='pep',
        parser_name='restructuredtext',
        writer_name='pep_html',
        settings=docutils_settings,
        # Allow Docutils traceback if there's an exception:
        settings_overrides={'traceback': 1})
    outfile.write(output)


def get_pep_type(input_lines):
    """
    Return the Content-Type of the input.  "text/plain" is the default.
    Return ``None`` if the input is not a PEP.
    """
    pep_type = None
    for line in input_lines:
        line = line.rstrip().lower()
        if not line:
            # End of the RFC 2822 header (first blank line).
            break
        elif line.startswith('content-type: '):
            pep_type = line.split()[1] or 'text/plain'
            break
        elif line.startswith('pep: '):
            # Default PEP type, used if no explicit content-type specified:
            pep_type = 'text/plain'
    return pep_type


def get_input_lines(inpath):
    try:
        infile = open(inpath)
    except IOError, e:
        if e.errno <> errno.ENOENT: raise
        print >> sys.stderr, 'Error: Skipping missing PEP file:', e.filename
        sys.stderr.flush()
        return None
    lines = infile.read().splitlines(1) # handles x-platform line endings
    infile.close()
    return lines


def find_pep(pep_str):
    """Find the .txt file indicated by a cmd line argument"""
    if os.path.exists(pep_str):
        return pep_str
    num = int(pep_str)
    return "pep-%04d.txt" % num

def make_html(inpath, verbose=0):
    input_lines = get_input_lines(inpath)
    if input_lines is None:
        return None
    pep_type = get_pep_type(input_lines)
    if pep_type is None:
        print >> sys.stderr, 'Error: Input file %s is not a PEP.' % inpath
        sys.stdout.flush()
        return None
    elif not PEP_TYPE_DISPATCH.has_key(pep_type):
        print >> sys.stderr, ('Error: Unknown PEP type for input file %s: %s'
                              % (inpath, pep_type))
        sys.stdout.flush()
        return None
    elif PEP_TYPE_DISPATCH[pep_type] == None:
        pep_type_error(inpath, pep_type)
        return None
    outpath = os.path.splitext(inpath)[0] + ".html"
    if verbose:
        print inpath, "(%s)" % pep_type, "->", outpath
        sys.stdout.flush()
    outfile = open(outpath, "w")
    PEP_TYPE_DISPATCH[pep_type](inpath, input_lines, outfile)
    outfile.close()
    os.chmod(outfile.name, 0664)
    return outpath

def push_pep(htmlfiles, txtfiles, username, verbose, local=0):
    quiet = ""
    if local:
        if verbose:
            quiet = "-v"
        target = HDIR
        copy_cmd = "cp"
        chmod_cmd = "chmod"
    else:
        if not verbose:
            quiet = "-q"
        if username:
            username = username + "@"
        target = username + HOST + ":" + HDIR
        copy_cmd = "scp"
        chmod_cmd = "ssh %s%s chmod" % (username, HOST)
    files = htmlfiles[:]
    files.extend(txtfiles)
    files.append("style.css")
    files.append("pep.css")
    filelist = SPACE.join(files)
    rc = os.system("%s %s %s %s" % (copy_cmd, quiet, filelist, target))
    if rc:
        sys.exit(rc)
##    rc = os.system("%s 664 %s/*" % (chmod_cmd, HDIR))
##    if rc:
##        sys.exit(rc)


PEP_TYPE_DISPATCH = {'text/plain': fixfile,
                     'text/x-rst': fix_rst_pep}
PEP_TYPE_MESSAGES = {}

def check_requirements():
    # Check Python:
    try:
        from email.Utils import parseaddr
    except ImportError:
        PEP_TYPE_DISPATCH['text/plain'] = None
        PEP_TYPE_MESSAGES['text/plain'] = (
            'Python %s or better required for "%%(pep_type)s" PEP '
            'processing; %s present (%%(inpath)s).'
            % (REQUIRES['python'], sys.version.split()[0]))
    # Check Docutils:
    try:
        import docutils
    except ImportError:
        PEP_TYPE_DISPATCH['text/x-rst'] = None
        PEP_TYPE_MESSAGES['text/x-rst'] = (
            'Docutils not present for "%(pep_type)s" PEP file %(inpath)s.  '
            'See README.txt for installation.')
    else:
        installed = [int(part) for part in docutils.__version__.split('.')]
        required = [int(part) for part in REQUIRES['docutils'].split('.')]
        if installed < required:
            PEP_TYPE_DISPATCH['text/x-rst'] = None
            PEP_TYPE_MESSAGES['text/x-rst'] = (
                'Docutils must be reinstalled for "%%(pep_type)s" PEP '
                'processing (%%(inpath)s).  Version %s or better required; '
                '%s present.  See README.txt for installation.'
                % (REQUIRES['docutils'], docutils.__version__))

def pep_type_error(inpath, pep_type):
    print >> sys.stderr, 'Error: ' + PEP_TYPE_MESSAGES[pep_type] % locals()
    sys.stdout.flush()


def browse_file(pep):
    import webbrowser
    file = find_pep(pep)
    if file.endswith(".txt"):
        file = file[:-3] + "html"
    file = os.path.abspath(file)
    url = "file:" + file
    webbrowser.open(url)

def browse_remote(pep):
    import webbrowser
    file = find_pep(pep)
    if file.endswith(".txt"):
        file = file[:-3] + "html"
    url = PEPDIRRUL + file
    webbrowser.open(url)


def main(argv=None):
    # defaults
    update = 0
    local = 0
    username = ''
    verbose = 1
    browse = 0

    check_requirements()

    if argv is None:
        argv = sys.argv[1:]

    try:
        opts, args = getopt.getopt(
            argv, 'bilhqu:',
            ['browse', 'install', 'local', 'help', 'quiet', 'user='])
    except getopt.error, msg:
        usage(1, msg)

    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt in ('-i', '--install'):
            update = 1
        elif opt in ('-l', '--local'):
            update = 1
            local = 1
        elif opt in ('-u', '--user'):
            username = arg
        elif opt in ('-q', '--quiet'):
            verbose = 0
        elif opt in ('-b', '--browse'):
            browse = 1

    if args:
        peptxt = []
        html = []
        for pep in args:
            file = find_pep(pep)
            peptxt.append(file)
            newfile = make_html(file, verbose=verbose)
            if newfile:
                html.append(newfile)
                if browse and not update:
                    browse_file(pep)
    else:
        # do them all
        peptxt = []
        html = []
        files = glob.glob("pep-*.txt")
        files.sort()
        for file in files:
            peptxt.append(file)
            newfile = make_html(file, verbose=verbose)
            if newfile:
                html.append(newfile)
        if browse and not update:
            browse_file("0")

    if update:
        push_pep(html, peptxt, username, verbose, local=local)
        if browse:
            if args:
                for pep in args:
                    browse_remote(pep)
            else:
                browse_remote("0")



if __name__ == "__main__":
    main()
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.