summaryrefslogtreecommitdiffstats
path: root/Lib/idlelib/AutoIndent.py
blob: eff398b527025cdc6a19ac0a1fa2fc7304f642f0 (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
519
520
import string
#from Tkinter import TclError
#import tkMessageBox
#import tkSimpleDialog

###$ event <<newline-and-indent>>
###$ win <Key-Return>
###$ win <KP_Enter>
###$ unix <Key-Return>
###$ unix <KP_Enter>

###$ event <<indent-region>>
###$ win <Control-bracketright>
###$ unix <Alt-bracketright>
###$ unix <Control-bracketright>

###$ event <<dedent-region>>
###$ win <Control-bracketleft>
###$ unix <Alt-bracketleft>
###$ unix <Control-bracketleft>

###$ event <<comment-region>>
###$ win <Alt-Key-3>
###$ unix <Alt-Key-3>

###$ event <<uncomment-region>>
###$ win <Alt-Key-4>
###$ unix <Alt-Key-4>

###$ event <<tabify-region>>
###$ win <Alt-Key-5>
###$ unix <Alt-Key-5>

###$ event <<untabify-region>>
###$ win <Alt-Key-6>
###$ unix <Alt-Key-6>

import PyParse

class AutoIndent:

    menudefs = [
        ('format', [       # /s/edit/format   dscherer@cmu.edu
            ('_Indent region', '<<indent-region>>'),
            ('_Dedent region', '<<dedent-region>>'),
            ('Comment _out region', '<<comment-region>>'),
            ('U_ncomment region', '<<uncomment-region>>'),
            ('Tabify region', '<<tabify-region>>'),
            ('Untabify region', '<<untabify-region>>'),
            ('Toggle tabs', '<<toggle-tabs>>'),
            ('New indent width', '<<change-indentwidth>>'),
        ]),
    ]

    # usetabs true  -> literal tab characters are used by indent and
    #                  dedent cmds, possibly mixed with spaces if
    #                  indentwidth is not a multiple of tabwidth
    #         false -> tab characters are converted to spaces by indent
    #                  and dedent cmds, and ditto TAB keystrokes
    # indentwidth is the number of characters per logical indent level.
    # tabwidth is the display width of a literal tab character.
    # CAUTION:  telling Tk to use anything other than its default
    # tab setting causes it to use an entirely different tabbing algorithm,
    # treating tab stops as fixed distances from the left margin.
    # Nobody expects this, so for now tabwidth should never be changed.
    usetabs = 1
    indentwidth = 4
    tabwidth = 8    # for IDLE use, must remain 8 until Tk is fixed

    # If context_use_ps1 is true, parsing searches back for a ps1 line;
    # else searches for a popular (if, def, ...) Python stmt.
    context_use_ps1 = 0

    # When searching backwards for a reliable place to begin parsing,
    # first start num_context_lines[0] lines back, then
    # num_context_lines[1] lines back if that didn't work, and so on.
    # The last value should be huge (larger than the # of lines in a
    # conceivable file).
    # Making the initial values larger slows things down more often.
    num_context_lines = 50, 500, 5000000

    def __init__(self, editwin):
        self.editwin = editwin
        self.text = editwin.text

    def config(self, **options):
        for key, value in options.items():
            if key == 'usetabs':
                self.usetabs = value
            elif key == 'indentwidth':
                self.indentwidth = value
            elif key == 'tabwidth':
                self.tabwidth = value
            elif key == 'context_use_ps1':
                self.context_use_ps1 = value
            else:
                raise KeyError, "bad option name: %s" % `key`

    # If ispythonsource and guess are true, guess a good value for
    # indentwidth based on file content (if possible), and if
    # indentwidth != tabwidth set usetabs false.
    # In any case, adjust the Text widget's view of what a tab
    # character means.

    def set_indentation_params(self, ispythonsource, guess=1):
        if guess and ispythonsource:
            i = self.guess_indent()
            if 2 <= i <= 8:
                self.indentwidth = i
            if self.indentwidth != self.tabwidth:
                self.usetabs = 0

        self.editwin.set_tabwidth(self.tabwidth)

    def smart_backspace_event(self, event):
        text = self.text
        first, last = self.editwin.get_selection_indices()
        if first and last:
            text.delete(first, last)
            text.mark_set("insert", first)
            return "break"
        # Delete whitespace left, until hitting a real char or closest
        # preceding virtual tab stop.
        chars = text.get("insert linestart", "insert")
        if chars == '':
            if text.compare("insert", ">", "1.0"):
                # easy: delete preceding newline
                text.delete("insert-1c")
            else:
                text.bell()     # at start of buffer
            return "break"
        if  chars[-1] not in " \t":
            # easy: delete preceding real char
            text.delete("insert-1c")
            return "break"
        # Ick.  It may require *inserting* spaces if we back up over a
        # tab character!  This is written to be clear, not fast.
        expand, tabwidth = string.expandtabs, self.tabwidth
        have = len(expand(chars, tabwidth))
        assert have > 0
        want = int((have - 1) / self.indentwidth) * self.indentwidth
        ncharsdeleted = 0
        while 1:
            chars = chars[:-1]
            ncharsdeleted = ncharsdeleted + 1
            have = len(expand(chars, tabwidth))
            if have <= want or chars[-1] not in " \t":
                break
        text.undo_block_start()
        text.delete("insert-%dc" % ncharsdeleted, "insert")
        if have < want:
            text.insert("insert", ' ' * (want - have))
        text.undo_block_stop()
        return "break"

    def smart_indent_event(self, event):
        # if intraline selection:
        #     delete it
        # elif multiline selection:
        #     do indent-region & return
        # indent one level
        text = self.text
        first, last = self.editwin.get_selection_indices()
        text.undo_block_start()
        try:
            if first and last:
                if index2line(first) != index2line(last):
                    return self.indent_region_event(event)
                text.delete(first, last)
                text.mark_set("insert", first)
            prefix = text.get("insert linestart", "insert")
            raw, effective = classifyws(prefix, self.tabwidth)
            if raw == len(prefix):
                # only whitespace to the left
                self.reindent_to(effective + self.indentwidth)
            else:
                if self.usetabs:
                    pad = '\t'
                else:
                    effective = len(string.expandtabs(prefix,
                                                      self.tabwidth))
                    n = self.indentwidth
                    pad = ' ' * (n - effective % n)
                text.insert("insert", pad)
            text.see("insert")
            return "break"
        finally:
            text.undo_block_stop()

    def newline_and_indent_event(self, event):
        text = self.text
        first, last = self.editwin.get_selection_indices()
        text.undo_block_start()
        try:
            if first and last:
                text.delete(first, last)
                text.mark_set("insert", first)
            line = text.get("insert linestart", "insert")
            i, n = 0, len(line)
            while i < n and line[i] in " \t":
                i = i+1
            if i == n:
                # the cursor is in or at leading indentation; just inject
                # an empty line at the start
                text.insert("insert linestart", '\n')
                return "break"
            indent = line[:i]
            # strip whitespace before insert point
            i = 0
            while line and line[-1] in " \t":
                line = line[:-1]
                i = i+1
            if i:
                text.delete("insert - %d chars" % i, "insert")
            # strip whitespace after insert point
            while text.get("insert") in " \t":
                text.delete("insert")
            # start new line
            text.insert("insert", '\n')

            # adjust indentation for continuations and block
            # open/close first need to find the last stmt
            lno = index2line(text.index('insert'))
            y = PyParse.Parser(self.indentwidth, self.tabwidth)
            for context in self.num_context_lines:
                startat = max(lno - context, 1)
                startatindex = `startat` + ".0"
                rawtext = text.get(startatindex, "insert")
                y.set_str(rawtext)
                bod = y.find_good_parse_start(
                          self.context_use_ps1,
                          self._build_char_in_string_func(startatindex))
                if bod is not None or startat == 1:
                    break
            y.set_lo(bod or 0)
            c = y.get_continuation_type()
            if c != PyParse.C_NONE:
                # The current stmt hasn't ended yet.
                if c == PyParse.C_STRING:
                    # inside a string; just mimic the current indent
                    text.insert("insert", indent)
                elif c == PyParse.C_BRACKET:
                    # line up with the first (if any) element of the
                    # last open bracket structure; else indent one
                    # level beyond the indent of the line with the
                    # last open bracket
                    self.reindent_to(y.compute_bracket_indent())
                elif c == PyParse.C_BACKSLASH:
                    # if more than one line in this stmt already, just
                    # mimic the current indent; else if initial line
                    # has a start on an assignment stmt, indent to
                    # beyond leftmost =; else to beyond first chunk of
                    # non-whitespace on initial line
                    if y.get_num_lines_in_stmt() > 1:
                        text.insert("insert", indent)
                    else:
                        self.reindent_to(y.compute_backslash_indent())
                else:
                    assert 0, "bogus continuation type " + `c`
                return "break"

            # This line starts a brand new stmt; indent relative to
            # indentation of initial line of closest preceding
            # interesting stmt.
            indent = y.get_base_indent_string()
            text.insert("insert", indent)
            if y.is_block_opener():
                self.smart_indent_event(event)
            elif indent and y.is_block_closer():
                self.smart_backspace_event(event)
            return "break"
        finally:
            text.see("insert")
            text.undo_block_stop()

    auto_indent = newline_and_indent_event

    # Our editwin provides a is_char_in_string function that works
    # with a Tk text index, but PyParse only knows about offsets into
    # a string. This builds a function for PyParse that accepts an
    # offset.

    def _build_char_in_string_func(self, startindex):
        def inner(offset, _startindex=startindex,
                  _icis=self.editwin.is_char_in_string):
            return _icis(_startindex + "+%dc" % offset)
        return inner

    def indent_region_event(self, event):
        head, tail, chars, lines = self.get_region()
        for pos in range(len(lines)):
            line = lines[pos]
            if line:
                raw, effective = classifyws(line, self.tabwidth)
                effective = effective + self.indentwidth
                lines[pos] = self._make_blanks(effective) + line[raw:]
        self.set_region(head, tail, chars, lines)
        return "break"

    def dedent_region_event(self, event):
        head, tail, chars, lines = self.get_region()
        for pos in range(len(lines)):
            line = lines[pos]
            if line:
                raw, effective = classifyws(line, self.tabwidth)
                effective = max(effective - self.indentwidth, 0)
                lines[pos] = self._make_blanks(effective) + line[raw:]
        self.set_region(head, tail, chars, lines)
        return "break"

    def comment_region_event(self, event):
        head, tail, chars, lines = self.get_region()
        for pos in range(len(lines) - 1):
            line = lines[pos]
            lines[pos] = '##' + line
        self.set_region(head, tail, chars, lines)

    def uncomment_region_event(self, event):
        head, tail, chars, lines = self.get_region()
        for pos in range(len(lines)):
            line = lines[pos]
            if not line:
                continue
            if line[:2] == '##':
                line = line[2:]
            elif line[:1] == '#':
                line = line[1:]
            lines[pos] = line
        self.set_region(head, tail, chars, lines)

    def tabify_region_event(self, event):
        head, tail, chars, lines = self.get_region()
        tabwidth = self._asktabwidth()
        for pos in range(len(lines)):
            line = lines[pos]
            if line:
                raw, effective = classifyws(line, tabwidth)
                ntabs, nspaces = divmod(effective, tabwidth)
                lines[pos] = '\t' * ntabs + ' ' * nspaces + line[raw:]
        self.set_region(head, tail, chars, lines)

    def untabify_region_event(self, event):
        head, tail, chars, lines = self.get_region()
        tabwidth = self._asktabwidth()
        for pos in range(len(lines)):
            lines[pos] = string.expandtabs(lines[pos], tabwidth)
        self.set_region(head, tail, chars, lines)

    def toggle_tabs_event(self, event):
        if self.editwin.askyesno(
              "Toggle tabs",
              "Turn tabs " + ("on", "off")[self.usetabs] + "?",
              parent=self.text):
            self.usetabs = not self.usetabs
        return "break"

    # XXX this isn't bound to anything -- see class tabwidth comments
    def change_tabwidth_event(self, event):
        new = self._asktabwidth()
        if new != self.tabwidth:
            self.tabwidth = new
            self.set_indentation_params(0, guess=0)
        return "break"

    def change_indentwidth_event(self, event):
        new = self.editwin.askinteger(
                  "Indent width",
                  "New indent width (1-16)",
                  parent=self.text,
                  initialvalue=self.indentwidth,
                  minvalue=1,
                  maxvalue=16)
        if new and new != self.indentwidth:
            self.indentwidth = new
        return "break"

    def get_region(self):
        text = self.text
        first, last = self.editwin.get_selection_indices()
        if first and last:
            head = text.index(first + " linestart")
            tail = text.index(last + "-1c lineend +1c")
        else:
            head = text.index("insert linestart")
            tail = text.index("insert lineend +1c")
        chars = text.get(head, tail)
        lines = string.split(chars, "\n")
        return head, tail, chars, lines

    def set_region(self, head, tail, chars, lines):
        text = self.text
        newchars = string.join(lines, "\n")
        if newchars == chars:
            text.bell()
            return
        text.tag_remove("sel", "1.0", "end")
        text.mark_set("insert", head)
        text.undo_block_start()
        text.delete(head, tail)
        text.insert(head, newchars)
        text.undo_block_stop()
        text.tag_add("sel", head, "insert")

    # Make string that displays as n leading blanks.

    def _make_blanks(self, n):
        if self.usetabs:
            ntabs, nspaces = divmod(n, self.tabwidth)
            return '\t' * ntabs + ' ' * nspaces
        else:
            return ' ' * n

    # Delete from beginning of line to insert point, then reinsert
    # column logical (meaning use tabs if appropriate) spaces.

    def reindent_to(self, column):
        text = self.text
        text.undo_block_start()
        if text.compare("insert linestart", "!=", "insert"):
            text.delete("insert linestart", "insert")
        if column:
            text.insert("insert", self._make_blanks(column))
        text.undo_block_stop()

    def _asktabwidth(self):
        return self.editwin.askinteger(
            "Tab width",
            "Spaces per tab?",
            parent=self.text,
            initialvalue=self.tabwidth,
            minvalue=1,
            maxvalue=16) or self.tabwidth

    # Guess indentwidth from text content.
    # Return guessed indentwidth.  This should not be believed unless
    # it's in a reasonable range (e.g., it will be 0 if no indented
    # blocks are found).

    def guess_indent(self):
        opener, indented = IndentSearcher(self.text, self.tabwidth).run()
        if opener and indented:
            raw, indentsmall = classifyws(opener, self.tabwidth)
            raw, indentlarge = classifyws(indented, self.tabwidth)
        else:
            indentsmall = indentlarge = 0
        return indentlarge - indentsmall

# "line.col" -> line, as an int
def index2line(index):
    return int(float(index))

# Look at the leading whitespace in s.
# Return pair (# of leading ws characters,
#              effective # of leading blanks after expanding
#              tabs to width tabwidth)

def classifyws(s, tabwidth):
    raw = effective = 0
    for ch in s:
        if ch == ' ':
            raw = raw + 1
            effective = effective + 1
        elif ch == '\t':
            raw = raw + 1
            effective = (effective / tabwidth + 1) * tabwidth
        else:
            break
    return raw, effective

import tokenize
_tokenize = tokenize
del tokenize

class IndentSearcher:

    # .run() chews over the Text widget, looking for a block opener
    # and the stmt following it.  Returns a pair,
    #     (line containing block opener, line containing stmt)
    # Either or both may be None.

    def __init__(self, text, tabwidth):
        self.text = text
        self.tabwidth = tabwidth
        self.i = self.finished = 0
        self.blkopenline = self.indentedline = None

    def readline(self):
        if self.finished:
            return ""
        i = self.i = self.i + 1
        mark = `i` + ".0"
        if self.text.compare(mark, ">=", "end"):
            return ""
        return self.text.get(mark, mark + " lineend+1c")

    def tokeneater(self, type, token, start, end, line,
                   INDENT=_tokenize.INDENT,
                   NAME=_tokenize.NAME,
                   OPENERS=('class', 'def', 'for', 'if', 'try', 'while')):
        if self.finished:
            pass
        elif type == NAME and token in OPENERS:
            self.blkopenline = line
        elif type == INDENT and self.blkopenline:
            self.indentedline = line
            self.finished = 1

    def run(self):
        save_tabsize = _tokenize.tabsize
        _tokenize.tabsize = self.tabwidth
        try:
            try:
                _tokenize.tokenize(self.readline, self.tokeneater)
            except _tokenize.TokenError:
                # since we cut off the tokenizer early, we can trigger
                # spurious errors
                pass
        finally:
            _tokenize.tabsize = save_tabsize
        return self.blkopenline, self.indentedline