Source

pypy-postgresql / lib_pypy / pyrepl / reader.py

Full commit
  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
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
#   Copyright 2000-2010 Michael Hudson-Doyle <micahel@gmail.com>
#                       Antonio Cuni
#                       Armin Rigo
#
#                        All Rights Reserved
#
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose is hereby granted without fee,
# provided that the above copyright notice appear in all copies and
# that both that copyright notice and this permission notice appear in
# supporting documentation.
#
# THE AUTHOR MICHAEL HUDSON DISCLAIMS ALL WARRANTIES WITH REGARD TO
# THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
# AND FITNESS, IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL,
# INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER
# RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF
# CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.

import types
from pyrepl import unicodedata_
from pyrepl import commands
from pyrepl import input

def _make_unctrl_map():
    uc_map = {}
    for c in map(unichr, range(256)):
        if unicodedata_.category(c)[0] <> 'C':
            uc_map[c] = c
    for i in range(32):
        c = unichr(i)
        uc_map[c] = u'^' + unichr(ord('A') + i - 1)
    uc_map['\t'] = '    ' # display TABs as 4 characters
    uc_map['\177'] = u'^?'
    for i in range(256):
        c = unichr(i)
        if not uc_map.has_key(c):
            uc_map[c] = u'\\%03o'%i
    return uc_map

# disp_str proved to be a bottleneck for large inputs, so it's been
# rewritten in C; it's not required though.
try:
    raise ImportError # currently it's borked by the unicode support

    from _pyrepl_utils import disp_str, init_unctrl_map

    init_unctrl_map(_make_unctrl_map())

    del init_unctrl_map
except ImportError:
    def _my_unctrl(c, u=_make_unctrl_map()):
        if c in u:
            return u[c]
        else:
            if unicodedata_.category(c).startswith('C'):
                return '\u%04x'%(ord(c),)
            else:
                return c

    def disp_str(buffer, join=''.join, uc=_my_unctrl):
        """ disp_str(buffer:string) -> (string, [int])

        Return the string that should be the printed represenation of
        |buffer| and a list detailing where the characters of |buffer|
        get used up.  E.g.:

        >>> disp_str(chr(3))
        ('^C', [1, 0])

        the list always contains 0s or 1s at present; it could conceivably
        go higher as and when unicode support happens."""
        s = map(uc, buffer)
        return (join(s),
                map(ord, join(map(lambda x:'\001'+(len(x)-1)*'\000', s))))

    del _my_unctrl

del _make_unctrl_map

# syntax classes:

[SYNTAX_WHITESPACE,
 SYNTAX_WORD,
 SYNTAX_SYMBOL] = range(3)

def make_default_syntax_table():
    # XXX perhaps should use some unicodedata here?
    st = {}
    for c in map(unichr, range(256)):
        st[c] = SYNTAX_SYMBOL
    for c in [a for a in map(unichr, range(256)) if a.isalpha()]:
        st[c] = SYNTAX_WORD
    st[u'\n'] = st[u' '] = SYNTAX_WHITESPACE
    return st

default_keymap = tuple(
    [(r'\C-a', 'beginning-of-line'),
     (r'\C-b', 'left'),
     (r'\C-c', 'interrupt'),
     (r'\C-d', 'delete'),
     (r'\C-e', 'end-of-line'),
     (r'\C-f', 'right'),
     (r'\C-g', 'cancel'),
     (r'\C-h', 'backspace'),
     (r'\C-j', 'accept'),
     (r'\<return>', 'accept'),
     (r'\C-k', 'kill-line'),
     (r'\C-l', 'clear-screen'),
     (r'\C-m', 'accept'),
     (r'\C-q', 'quoted-insert'),
     (r'\C-t', 'transpose-characters'),
     (r'\C-u', 'unix-line-discard'),
     (r'\C-v', 'quoted-insert'),
     (r'\C-w', 'unix-word-rubout'),
     (r'\C-x\C-u', 'upcase-region'),
     (r'\C-y', 'yank'),
     (r'\C-z', 'suspend'),

     (r'\M-b', 'backward-word'),
     (r'\M-c', 'capitalize-word'),
     (r'\M-d', 'kill-word'),
     (r'\M-f', 'forward-word'),
     (r'\M-l', 'downcase-word'),
     (r'\M-t', 'transpose-words'),
     (r'\M-u', 'upcase-word'),
     (r'\M-y', 'yank-pop'),
     (r'\M--', 'digit-arg'),
     (r'\M-0', 'digit-arg'),
     (r'\M-1', 'digit-arg'),
     (r'\M-2', 'digit-arg'),
     (r'\M-3', 'digit-arg'),
     (r'\M-4', 'digit-arg'),
     (r'\M-5', 'digit-arg'),
     (r'\M-6', 'digit-arg'),
     (r'\M-7', 'digit-arg'),
     (r'\M-8', 'digit-arg'),
     (r'\M-9', 'digit-arg'),
     #(r'\M-\n', 'insert-nl'),
     ('\\\\', 'self-insert')] + \
    [(c, 'self-insert')
     for c in map(chr, range(32, 127)) if c <> '\\'] + \
    [(c, 'self-insert')
     for c in map(chr, range(128, 256)) if c.isalpha()] + \
    [(r'\<up>', 'up'),
     (r'\<down>', 'down'),
     (r'\<left>', 'left'),
     (r'\<right>', 'right'),
     (r'\<insert>', 'quoted-insert'),
     (r'\<delete>', 'delete'),
     (r'\<backspace>', 'backspace'),
     (r'\M-\<backspace>', 'backward-kill-word'),
     (r'\<end>', 'end-of-line'),         # was 'end'
     (r'\<home>', 'beginning-of-line'),  # was 'home'
     (r'\<f1>', 'help'),
     (r'\EOF', 'end'),  # the entries in the terminfo database for xterms
     (r'\EOH', 'home'), # seem to be wrong.  this is a less than ideal
                        # workaround
     ])

del c # from the listcomps

class Reader(object):
    """The Reader class implements the bare bones of a command reader,
    handling such details as editing and cursor motion.  What it does
    not support are such things as completion or history support -
    these are implemented elsewhere.

    Instance variables of note include:

      * buffer:
        A *list* (*not* a string at the moment :-) containing all the
        characters that have been entered.
      * console:
        Hopefully encapsulates the OS dependent stuff.
      * pos:
        A 0-based index into `buffer' for where the insertion point
        is.
      * screeninfo:
        Ahem.  This list contains some info needed to move the
        insertion point around reasonably efficiently.  I'd like to
        get rid of it, because its contents are obtuse (to put it
        mildly) but I haven't worked out if that is possible yet.
      * cxy, lxy:
        the position of the insertion point in screen ... XXX
      * syntax_table:
        Dictionary mapping characters to `syntax class'; read the
        emacs docs to see what this means :-)
      * commands:
        Dictionary mapping command names to command classes.
      * arg:
        The emacs-style prefix argument.  It will be None if no such
        argument has been provided.
      * dirty:
        True if we need to refresh the display.
      * kill_ring:
        The emacs-style kill-ring; manipulated with yank & yank-pop
      * ps1, ps2, ps3, ps4:
        prompts.  ps1 is the prompt for a one-line input; for a
        multiline input it looks like:
            ps2> first line of input goes here
            ps3> second and further
            ps3> lines get ps3
            ...
            ps4> and the last one gets ps4
        As with the usual top-level, you can set these to instances if
        you like; str() will be called on them (once) at the beginning
        of each command.  Don't put really long or newline containing
        strings here, please!
        This is just the default policy; you can change it freely by
        overriding get_prompt() (and indeed some standard subclasses
        do).
      * finished:
        handle1 will set this to a true value if a command signals
        that we're done.
    """

    help_text = """\
This is pyrepl.  Hear my roar.

Helpful text may appear here at some point in the future when I'm
feeling more loquacious than I am now."""

    msg_at_bottom = True

    def __init__(self, console):
        self.buffer = []
        self.ps1 = "->> "
        self.ps2 = "/>> "
        self.ps3 = "|.. "
        self.ps4 = "\__ "
        self.kill_ring = []
        self.arg = None
        self.finished = 0
        self.console = console
        self.commands = {}
        self.msg = ''
        for v in vars(commands).values():
            if  ( isinstance(v, type)
                  and issubclass(v, commands.Command)
                  and v.__name__[0].islower() ):
                self.commands[v.__name__] = v
                self.commands[v.__name__.replace('_', '-')] = v
        self.syntax_table = make_default_syntax_table()
        self.input_trans_stack = []
        self.keymap = self.collect_keymap()
        self.input_trans = input.KeymapTranslator(
            self.keymap,
            invalid_cls='invalid-key',
            character_cls='self-insert')

    def collect_keymap(self):
        return default_keymap

    def calc_screen(self):
        """The purpose of this method is to translate changes in
        self.buffer into changes in self.screen.  Currently it rips
        everything down and starts from scratch, which whilst not
        especially efficient is certainly simple(r).
        """
        lines = self.get_unicode().split("\n")
        screen = []
        screeninfo = []
        w = self.console.width - 1
        p = self.pos
        for ln, line in zip(range(len(lines)), lines):
            ll = len(line)
            if 0 <= p <= ll:
                if self.msg and not self.msg_at_bottom:
                    for mline in self.msg.split("\n"):
                        screen.append(mline)
                        screeninfo.append((0, []))
                self.lxy = p, ln
            prompt = self.get_prompt(ln, ll >= p >= 0)
            while '\n' in prompt:
                pre_prompt, _, prompt = prompt.partition('\n')
                screen.append(pre_prompt)
                screeninfo.append((0, []))
            p -= ll + 1
            prompt, lp = self.process_prompt(prompt)
            l, l2 = disp_str(line)
            wrapcount = (len(l) + lp) / w
            if wrapcount == 0:
                screen.append(prompt + l)
                screeninfo.append((lp, l2+[1]))
            else:
                screen.append(prompt + l[:w-lp] + "\\")
                screeninfo.append((lp, l2[:w-lp]))
                for i in range(-lp + w, -lp + wrapcount*w, w):
                    screen.append(l[i:i+w] +  "\\")
                    screeninfo.append((0, l2[i:i + w]))
                screen.append(l[wrapcount*w - lp:])
                screeninfo.append((0, l2[wrapcount*w - lp:]+[1]))
        self.screeninfo = screeninfo
        self.cxy = self.pos2xy(self.pos)
        if self.msg and self.msg_at_bottom:
            for mline in self.msg.split("\n"):
                screen.append(mline)
                screeninfo.append((0, []))
        return screen

    def process_prompt(self, prompt):
        """ Process the prompt.

        This means calculate the length of the prompt. The character \x01
        and \x02 are used to bracket ANSI control sequences and need to be
        excluded from the length calculation.  So also a copy of the prompt
        is returned with these control characters removed.  """

        out_prompt = ''
        l = len(prompt)
        pos = 0
        while True:
            s = prompt.find('\x01', pos)
            if s == -1:
                break
            e = prompt.find('\x02', s)
            if e == -1:
                break
            # Found start and end brackets, subtract from string length
            l = l - (e-s+1)
            out_prompt += prompt[pos:s] + prompt[s+1:e]
            pos = e+1
        out_prompt += prompt[pos:]
        return out_prompt, l

    def bow(self, p=None):
        """Return the 0-based index of the word break preceding p most
        immediately.

        p defaults to self.pos; word boundaries are determined using
        self.syntax_table."""
        if p is None:
            p = self.pos
        st = self.syntax_table
        b = self.buffer
        p -= 1
        while p >= 0 and st.get(b[p], SYNTAX_WORD) <> SYNTAX_WORD:
            p -= 1
        while p >= 0 and st.get(b[p], SYNTAX_WORD) == SYNTAX_WORD:
            p -= 1
        return p + 1

    def eow(self, p=None):
        """Return the 0-based index of the word break following p most
        immediately.

        p defaults to self.pos; word boundaries are determined using
        self.syntax_table."""
        if p is None:
            p = self.pos
        st = self.syntax_table
        b = self.buffer
        while p < len(b) and st.get(b[p], SYNTAX_WORD) <> SYNTAX_WORD:
            p += 1
        while p < len(b) and st.get(b[p], SYNTAX_WORD) == SYNTAX_WORD:
            p += 1
        return p

    def bol(self, p=None):
        """Return the 0-based index of the line break preceding p most
        immediately.

        p defaults to self.pos."""
        # XXX there are problems here.
        if p is None:
            p = self.pos
        b = self.buffer
        p -= 1
        while p >= 0 and b[p] <> '\n':
            p -= 1
        return p + 1

    def eol(self, p=None):
        """Return the 0-based index of the line break following p most
        immediately.

        p defaults to self.pos."""
        if p is None:
            p = self.pos
        b = self.buffer
        while p < len(b) and b[p] <> '\n':
            p += 1
        return p

    def get_arg(self, default=1):
        """Return any prefix argument that the user has supplied,
        returning `default' if there is None.  `default' defaults
        (groan) to 1."""
        if self.arg is None:
            return default
        else:
            return self.arg

    def get_prompt(self, lineno, cursor_on_line):
        """Return what should be in the left-hand margin for line
        `lineno'."""
        if self.arg is not None and cursor_on_line:
            return "(arg: %s) "%self.arg
        if "\n" in self.buffer:
            if lineno == 0:
                res = self.ps2
            elif lineno == self.buffer.count("\n"):
                res = self.ps4
            else:
                res = self.ps3
        else:
            res = self.ps1
        # Lazily call str() on self.psN, and cache the results using as key
        # the object on which str() was called.  This ensures that even if the
        # same object is used e.g. for ps1 and ps2, str() is called only once.
        if res not in self._pscache:
            self._pscache[res] = str(res)
        return self._pscache[res]

    def push_input_trans(self, itrans):
        self.input_trans_stack.append(self.input_trans)
        self.input_trans = itrans

    def pop_input_trans(self):
        self.input_trans = self.input_trans_stack.pop()

    def pos2xy(self, pos):
        """Return the x, y coordinates of position 'pos'."""
        # this *is* incomprehensible, yes.
        y = 0
        assert 0 <= pos <= len(self.buffer)
        if pos == len(self.buffer):
            y = len(self.screeninfo) - 1
            p, l2 = self.screeninfo[y]
            return p + len(l2) - 1, y
        else:
            for p, l2 in self.screeninfo:
                l = l2.count(1)
                if l > pos:
                    break
                else:
                    pos -= l
                    y += 1
            c = 0
            i = 0
            while c < pos:
                c += l2[i]
                i += 1
            while l2[i] == 0:
                i += 1
            return p + i, y

    def insert(self, text):
        """Insert 'text' at the insertion point."""
        self.buffer[self.pos:self.pos] = list(text)
        self.pos += len(text)
        self.dirty = 1

    def update_cursor(self):
        """Move the cursor to reflect changes in self.pos"""
        self.cxy = self.pos2xy(self.pos)
        self.console.move_cursor(*self.cxy)

    def after_command(self, cmd):
        """This function is called to allow post command cleanup."""
        if getattr(cmd, "kills_digit_arg", 1):
            if self.arg is not None:
                self.dirty = 1
            self.arg = None

    def prepare(self):
        """Get ready to run.  Call restore when finished.  You must not
        write to the console in between the calls to prepare and
        restore."""
        try:
            self.console.prepare()
            self.arg = None
            self.screeninfo = []
            self.finished = 0
            del self.buffer[:]
            self.pos = 0
            self.dirty = 1
            self.last_command = None
            self._pscache = {}
        except:
            self.restore()
            raise

    def last_command_is(self, klass):
        if not self.last_command:
            return 0
        return issubclass(klass, self.last_command)

    def restore(self):
        """Clean up after a run."""
        self.console.restore()

    def finish(self):
        """Called when a command signals that we're finished."""
        pass

    def error(self, msg="none"):
        self.msg = "! " + msg + " "
        self.dirty = 1
        self.console.beep()

    def update_screen(self):
        if self.dirty:
            self.refresh()

    def refresh(self):
        """Recalculate and refresh the screen."""
        # this call sets up self.cxy, so call it first.
        screen = self.calc_screen()
        self.console.refresh(screen, self.cxy)
        self.dirty = 0 # forgot this for a while (blush)

    def do_cmd(self, cmd):
        #print cmd
        if isinstance(cmd[0], str):
            cmd = self.commands.get(cmd[0],
                                    commands.invalid_command)(self, cmd)
        elif isinstance(cmd[0], type):
            cmd = cmd[0](self, cmd)

        cmd.do()

        self.after_command(cmd)

        if self.dirty:
            self.refresh()
        else:
            self.update_cursor()

        if not isinstance(cmd, commands.digit_arg):
            self.last_command = cmd.__class__

        self.finished = cmd.finish
        if self.finished:
            self.console.finish()
            self.finish()

    def handle1(self, block=1):
        """Handle a single event.  Wait as long as it takes if block
        is true (the default), otherwise return None if no event is
        pending."""

        if self.msg:
            self.msg = ''
            self.dirty = 1

        while 1:
            event = self.console.get_event(block)
            if not event: # can only happen if we're not blocking
                return None

            if event.evt == 'key':
                self.input_trans.push(event)
            elif event.evt == 'scroll':
                self.refresh()
            elif event.evt == 'resize':
                self.refresh()
            else:
                pass

            cmd = self.input_trans.get()

            if cmd is None:
                if block:
                    continue
                else:
                    return None

            self.do_cmd(cmd)
            return 1

    def push_char(self, char):
        self.console.push_char(char)
        self.handle1(0)

    def readline(self, returns_unicode=False, startup_hook=None):
        """Read a line.  The implementation of this method also shows
        how to drive Reader if you want more control over the event
        loop."""
        self.prepare()
        try:
            if startup_hook is not None:
                startup_hook()
            self.refresh()
            while not self.finished:
                self.handle1()
            if returns_unicode:
                return self.get_unicode()
            return self.get_buffer()
        finally:
            self.restore()

    def bind(self, spec, command):
        self.keymap = self.keymap + ((spec, command),)
        self.input_trans = input.KeymapTranslator(
            self.keymap,
            invalid_cls='invalid-key',
            character_cls='self-insert')

    def get_buffer(self, encoding=None):
        if encoding is None:
            encoding = self.console.encoding
        return u''.join(self.buffer).encode(self.console.encoding)

    def get_unicode(self):
        """Return the current buffer as a unicode string."""
        return u''.join(self.buffer)

def test():
    from pyrepl.unix_console import UnixConsole
    reader = Reader(UnixConsole())
    reader.ps1 = "**> "
    reader.ps2 = "/*> "
    reader.ps3 = "|*> "
    reader.ps4 = "\*> "
    while reader.readline():
        pass

if __name__=='__main__':
    test()