This repository was archived by the owner on Feb 13, 2025. It is now read-only.
forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 64
Expand file tree
/
Copy pathunicode_format.h
More file actions
1284 lines (1115 loc) · 40.1 KB
/
unicode_format.h
File metadata and controls
1284 lines (1115 loc) · 40.1 KB
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
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
unicode_format.h -- implementation of str.format().
*/
/************************************************************************/
/*********** Global data structures and forward declarations *********/
/************************************************************************/
/*
A SubString consists of the characters between two string or
unicode pointers.
*/
typedef struct {
PyObject *str; /* borrowed reference */
Py_ssize_t start, end;
} SubString;
typedef enum {
ANS_INIT,
ANS_AUTO,
ANS_MANUAL
} AutoNumberState; /* Keep track if we're auto-numbering fields */
/* Keeps track of our auto-numbering state, and which number field we're on */
typedef struct {
AutoNumberState an_state;
int an_field_number;
} AutoNumber;
/* forward declaration for recursion */
static PyObject *
build_string(SubString *input, PyObject *args, PyObject *kwargs,
int recursion_depth, AutoNumber *auto_number);
/************************************************************************/
/************************** Utility functions ************************/
/************************************************************************/
static void
AutoNumber_Init(AutoNumber *auto_number)
{
auto_number->an_state = ANS_INIT;
auto_number->an_field_number = 0;
}
/* fill in a SubString from a pointer and length */
Py_LOCAL_INLINE(void)
SubString_init(SubString *str, PyObject *s, Py_ssize_t start, Py_ssize_t end)
{
str->str = s;
str->start = start;
str->end = end;
}
/* return a new string. if str->str is NULL, return None */
Py_LOCAL_INLINE(PyObject *)
SubString_new_object(SubString *str)
{
if (str->str == NULL) {
Py_INCREF(Py_None);
return Py_None;
}
return PyUnicode_Substring(str->str, str->start, str->end);
}
/* return a new string. if str->str is NULL, return None */
Py_LOCAL_INLINE(PyObject *)
SubString_new_object_or_empty(SubString *str)
{
if (str->str == NULL) {
return PyUnicode_New(0, 0);
}
return SubString_new_object(str);
}
/* Return 1 if an error has been detected switching between automatic
field numbering and manual field specification, else return 0. Set
ValueError on error. */
static int
autonumber_state_error(AutoNumberState state, int field_name_is_empty)
{
if (state == ANS_MANUAL) {
if (field_name_is_empty) {
PyErr_SetString(PyExc_ValueError, "cannot switch from "
"manual field specification to "
"automatic field numbering");
return 1;
}
}
else {
if (!field_name_is_empty) {
PyErr_SetString(PyExc_ValueError, "cannot switch from "
"automatic field numbering to "
"manual field specification");
return 1;
}
}
return 0;
}
/************************************************************************/
/*********** Format string parsing -- integers and identifiers *********/
/************************************************************************/
static Py_ssize_t
get_integer(const SubString *str)
{
Py_ssize_t accumulator = 0;
Py_ssize_t digitval;
Py_ssize_t i;
/* empty string is an error */
if (str->start >= str->end)
return -1;
for (i = str->start; i < str->end; i++) {
digitval = Py_UNICODE_TODECIMAL(PyUnicode_READ_CHAR(str->str, i));
if (digitval < 0)
return -1;
/*
Detect possible overflow before it happens:
accumulator * 10 + digitval > PY_SSIZE_T_MAX if and only if
accumulator > (PY_SSIZE_T_MAX - digitval) / 10.
*/
if (accumulator > (PY_SSIZE_T_MAX - digitval) / 10) {
PyErr_Format(PyExc_ValueError,
"Too many decimal digits in format string");
return -1;
}
accumulator = accumulator * 10 + digitval;
}
return accumulator;
}
/************************************************************************/
/******** Functions to get field objects and specification strings ******/
/************************************************************************/
/* do the equivalent of obj.name */
static PyObject *
getattr(PyObject *obj, SubString *name)
{
PyObject *newobj;
PyObject *str = SubString_new_object(name);
if (str == NULL)
return NULL;
newobj = PyObject_GetAttr(obj, str);
Py_DECREF(str);
return newobj;
}
/* do the equivalent of obj[idx], where obj is a sequence */
static PyObject *
getitem_sequence(PyObject *obj, Py_ssize_t idx)
{
return PySequence_GetItem(obj, idx);
}
/* do the equivalent of obj[idx], where obj is not a sequence */
static PyObject *
getitem_idx(PyObject *obj, Py_ssize_t idx)
{
PyObject *newobj;
PyObject *idx_obj = PyLong_FromSsize_t(idx);
if (idx_obj == NULL)
return NULL;
newobj = PyObject_GetItem(obj, idx_obj);
Py_DECREF(idx_obj);
return newobj;
}
/* do the equivalent of obj[name] */
static PyObject *
getitem_str(PyObject *obj, SubString *name)
{
PyObject *newobj;
PyObject *str = SubString_new_object(name);
if (str == NULL)
return NULL;
newobj = PyObject_GetItem(obj, str);
Py_DECREF(str);
return newobj;
}
typedef struct {
/* the entire string we're parsing. we assume that someone else
is managing its lifetime, and that it will exist for the
lifetime of the iterator. can be empty */
SubString str;
/* index to where we are inside field_name */
Py_ssize_t index;
} FieldNameIterator;
static int
FieldNameIterator_init(FieldNameIterator *self, PyObject *s,
Py_ssize_t start, Py_ssize_t end)
{
SubString_init(&self->str, s, start, end);
self->index = start;
return 1;
}
static int
_FieldNameIterator_attr(FieldNameIterator *self, SubString *name)
{
Py_UCS4 c;
name->str = self->str.str;
name->start = self->index;
/* return everything until '.' or '[' */
while (self->index < self->str.end) {
c = PyUnicode_READ_CHAR(self->str.str, self->index++);
switch (c) {
case '[':
case '.':
/* backup so that we this character will be seen next time */
self->index--;
break;
default:
continue;
}
break;
}
/* end of string is okay */
name->end = self->index;
return 1;
}
static int
_FieldNameIterator_item(FieldNameIterator *self, SubString *name)
{
int bracket_seen = 0;
Py_UCS4 c;
name->str = self->str.str;
name->start = self->index;
/* return everything until ']' */
while (self->index < self->str.end) {
c = PyUnicode_READ_CHAR(self->str.str, self->index++);
switch (c) {
case ']':
bracket_seen = 1;
break;
default:
continue;
}
break;
}
/* make sure we ended with a ']' */
if (!bracket_seen) {
PyErr_SetString(PyExc_ValueError, "Missing ']' in format string");
return 0;
}
/* end of string is okay */
/* don't include the ']' */
name->end = self->index-1;
return 1;
}
/* returns 0 on error, 1 on non-error termination, and 2 if it returns a value */
static int
FieldNameIterator_next(FieldNameIterator *self, int *is_attribute,
Py_ssize_t *name_idx, SubString *name)
{
/* check at end of input */
if (self->index >= self->str.end)
return 1;
switch (PyUnicode_READ_CHAR(self->str.str, self->index++)) {
case '.':
*is_attribute = 1;
if (_FieldNameIterator_attr(self, name) == 0)
return 0;
*name_idx = -1;
break;
case '[':
*is_attribute = 0;
if (_FieldNameIterator_item(self, name) == 0)
return 0;
*name_idx = get_integer(name);
if (*name_idx == -1 && PyErr_Occurred())
return 0;
break;
default:
/* Invalid character follows ']' */
PyErr_SetString(PyExc_ValueError, "Only '.' or '[' may "
"follow ']' in format field specifier");
return 0;
}
/* empty string is an error */
if (name->start == name->end) {
PyErr_SetString(PyExc_ValueError, "Empty attribute in format string");
return 0;
}
return 2;
}
/* input: field_name
output: 'first' points to the part before the first '[' or '.'
'first_idx' is -1 if 'first' is not an integer, otherwise
it's the value of first converted to an integer
'rest' is an iterator to return the rest
*/
static int
field_name_split(PyObject *str, Py_ssize_t start, Py_ssize_t end, SubString *first,
Py_ssize_t *first_idx, FieldNameIterator *rest,
AutoNumber *auto_number)
{
Py_UCS4 c;
Py_ssize_t i = start;
int field_name_is_empty;
int using_numeric_index;
/* find the part up until the first '.' or '[' */
while (i < end) {
switch (c = PyUnicode_READ_CHAR(str, i++)) {
case '[':
case '.':
/* backup so that we this character is available to the
"rest" iterator */
i--;
break;
default:
continue;
}
break;
}
/* set up the return values */
SubString_init(first, str, start, i);
FieldNameIterator_init(rest, str, i, end);
/* see if "first" is an integer, in which case it's used as an index */
*first_idx = get_integer(first);
if (*first_idx == -1 && PyErr_Occurred())
return 0;
field_name_is_empty = first->start >= first->end;
/* If the field name is omitted or if we have a numeric index
specified, then we're doing numeric indexing into args. */
using_numeric_index = field_name_is_empty || *first_idx != -1;
/* We always get here exactly one time for each field we're
processing. And we get here in field order (counting by left
braces). So this is the perfect place to handle automatic field
numbering if the field name is omitted. */
/* Check if we need to do the auto-numbering. It's not needed if
we're called from string.Format routines, because it's handled
in that class by itself. */
if (auto_number) {
/* Initialize our auto numbering state if this is the first
time we're either auto-numbering or manually numbering. */
if (auto_number->an_state == ANS_INIT && using_numeric_index)
auto_number->an_state = field_name_is_empty ?
ANS_AUTO : ANS_MANUAL;
/* Make sure our state is consistent with what we're doing
this time through. Only check if we're using a numeric
index. */
if (using_numeric_index)
if (autonumber_state_error(auto_number->an_state,
field_name_is_empty))
return 0;
/* Zero length field means we want to do auto-numbering of the
fields. */
if (field_name_is_empty)
*first_idx = (auto_number->an_field_number)++;
}
return 1;
}
/*
get_field_object returns the object inside {}, before the
format_spec. It handles getindex and getattr lookups and consumes
the entire input string.
*/
static PyObject *
get_field_object(SubString *input, PyObject *args, PyObject *kwargs,
AutoNumber *auto_number)
{
PyObject *obj = NULL;
int ok;
int is_attribute;
SubString name;
SubString first;
Py_ssize_t index;
FieldNameIterator rest;
if (!field_name_split(input->str, input->start, input->end, &first,
&index, &rest, auto_number)) {
goto error;
}
if (index == -1) {
/* look up in kwargs */
PyObject *key = SubString_new_object(&first);
if (key == NULL)
goto error;
/* Use PyObject_GetItem instead of PyDict_GetItem because this
code is no longer just used with kwargs. It might be passed
a non-dict when called through format_map. */
if ((kwargs == NULL) || (obj = PyObject_GetItem(kwargs, key)) == NULL) {
PyErr_SetObject(PyExc_KeyError, key);
Py_DECREF(key);
goto error;
}
Py_DECREF(key);
}
else {
/* If args is NULL, we have a format string with a positional field
with only kwargs to retrieve it from. This can only happen when
used with format_map(), where positional arguments are not
allowed. */
if (args == NULL) {
PyErr_SetString(PyExc_ValueError, "Format string contains "
"positional fields");
goto error;
}
/* look up in args */
obj = PySequence_GetItem(args, index);
if (obj == NULL)
goto error;
}
/* iterate over the rest of the field_name */
while ((ok = FieldNameIterator_next(&rest, &is_attribute, &index,
&name)) == 2) {
PyObject *tmp;
if (is_attribute)
/* getattr lookup "." */
tmp = getattr(obj, &name);
else
/* getitem lookup "[]" */
if (index == -1)
tmp = getitem_str(obj, &name);
else
if (PySequence_Check(obj))
tmp = getitem_sequence(obj, index);
else
/* not a sequence */
tmp = getitem_idx(obj, index);
if (tmp == NULL)
goto error;
/* assign to obj */
Py_DECREF(obj);
obj = tmp;
}
/* end of iterator, this is the non-error case */
if (ok == 1)
return obj;
error:
Py_XDECREF(obj);
return NULL;
}
/************************************************************************/
/***************** Field rendering functions **************************/
/************************************************************************/
/*
render_field() is the main function in this section. It takes the
field object and field specification string generated by
get_field_and_spec, and renders the field into the output string.
render_field calls fieldobj.__format__(format_spec) method, and
appends to the output.
*/
static int
render_field(PyObject *fieldobj, SubString *format_spec, _PyUnicodeWriter *writer)
{
int ok = 0;
PyObject *result = NULL;
PyObject *format_spec_object = NULL;
int (*formatter) (_PyUnicodeWriter*, PyObject *, PyObject *, Py_ssize_t, Py_ssize_t) = NULL;
int err;
/* If we know the type exactly, skip the lookup of __format__ and just
call the formatter directly. */
if (PyUnicode_CheckExact(fieldobj))
formatter = _PyUnicode_FormatAdvancedWriter;
else if (PyLong_CheckExact(fieldobj))
formatter = _PyLong_FormatAdvancedWriter;
else if (PyFloat_CheckExact(fieldobj))
formatter = _PyFloat_FormatAdvancedWriter;
else if (PyComplex_CheckExact(fieldobj))
formatter = _PyComplex_FormatAdvancedWriter;
if (formatter) {
/* we know exactly which formatter will be called when __format__ is
looked up, so call it directly, instead. */
err = formatter(writer, fieldobj, format_spec->str,
format_spec->start, format_spec->end);
return (err == 0);
}
else {
/* We need to create an object out of the pointers we have, because
__format__ takes a string/unicode object for format_spec. */
if (format_spec->str)
format_spec_object = PyUnicode_Substring(format_spec->str,
format_spec->start,
format_spec->end);
else
format_spec_object = PyUnicode_New(0, 0);
if (format_spec_object == NULL)
goto done;
result = PyObject_Format(fieldobj, format_spec_object);
}
if (result == NULL)
goto done;
if (_PyUnicodeWriter_WriteStr(writer, result) == -1)
goto done;
ok = 1;
done:
Py_XDECREF(format_spec_object);
Py_XDECREF(result);
return ok;
}
static int
parse_field(SubString *str, SubString *field_name, SubString *format_spec,
int *format_spec_needs_expanding, Py_UCS4 *conversion)
{
/* Note this function works if the field name is zero length,
which is good. Zero length field names are handled later, in
field_name_split. */
Py_UCS4 c = 0;
/* initialize these, as they may be empty */
*conversion = '\0';
SubString_init(format_spec, NULL, 0, 0);
/* Search for the field name. it's terminated by the end of
the string, or a ':' or '!' */
field_name->str = str->str;
field_name->start = str->start;
while (str->start < str->end) {
switch ((c = PyUnicode_READ_CHAR(str->str, str->start++))) {
case '{':
PyErr_SetString(PyExc_ValueError, "unexpected '{' in field name");
return 0;
case '[':
for (; str->start < str->end; str->start++)
if (PyUnicode_READ_CHAR(str->str, str->start) == ']')
break;
continue;
case '}':
case ':':
case '!':
break;
default:
continue;
}
break;
}
field_name->end = str->start - 1;
if (c == '!' || c == ':') {
Py_ssize_t count;
/* we have a format specifier and/or a conversion */
/* don't include the last character */
/* see if there's a conversion specifier */
if (c == '!') {
/* there must be another character present */
if (str->start >= str->end) {
PyErr_SetString(PyExc_ValueError,
"end of string while looking for conversion "
"specifier");
return 0;
}
*conversion = PyUnicode_READ_CHAR(str->str, str->start++);
if (str->start < str->end) {
c = PyUnicode_READ_CHAR(str->str, str->start++);
if (c == '}')
return 1;
if (c != ':') {
PyErr_SetString(PyExc_ValueError,
"expected ':' after conversion specifier");
return 0;
}
}
}
format_spec->str = str->str;
format_spec->start = str->start;
count = 1;
while (str->start < str->end) {
switch ((c = PyUnicode_READ_CHAR(str->str, str->start++))) {
case '{':
*format_spec_needs_expanding = 1;
count++;
break;
case '}':
count--;
if (count == 0) {
format_spec->end = str->start - 1;
return 1;
}
break;
default:
break;
}
}
PyErr_SetString(PyExc_ValueError, "unmatched '{' in format spec");
return 0;
}
else if (c != '}') {
PyErr_SetString(PyExc_ValueError, "expected '}' before end of string");
return 0;
}
return 1;
}
/************************************************************************/
/******* Output string allocation and escape-to-markup processing ******/
/************************************************************************/
/* MarkupIterator breaks the string into pieces of either literal
text, or things inside {} that need to be marked up. it is
designed to make it easy to wrap a Python iterator around it, for
use with the Formatter class */
typedef struct {
SubString str;
} MarkupIterator;
static int
MarkupIterator_init(MarkupIterator *self, PyObject *str,
Py_ssize_t start, Py_ssize_t end)
{
SubString_init(&self->str, str, start, end);
return 1;
}
/* returns 0 on error, 1 on non-error termination, and 2 if it got a
string (or something to be expanded) */
static int
MarkupIterator_next(MarkupIterator *self, SubString *literal,
int *field_present, SubString *field_name,
SubString *format_spec, Py_UCS4 *conversion,
int *format_spec_needs_expanding)
{
int at_end;
Py_UCS4 c = 0;
Py_ssize_t start;
Py_ssize_t len;
int markup_follows = 0;
/* initialize all of the output variables */
SubString_init(literal, NULL, 0, 0);
SubString_init(field_name, NULL, 0, 0);
SubString_init(format_spec, NULL, 0, 0);
*conversion = '\0';
*format_spec_needs_expanding = 0;
*field_present = 0;
/* No more input, end of iterator. This is the normal exit
path. */
if (self->str.start >= self->str.end)
return 1;
start = self->str.start;
/* First read any literal text. Read until the end of string, an
escaped '{' or '}', or an unescaped '{'. In order to never
allocate memory and so I can just pass pointers around, if
there's an escaped '{' or '}' then we'll return the literal
including the brace, but no format object. The next time
through, we'll return the rest of the literal, skipping past
the second consecutive brace. */
while (self->str.start < self->str.end) {
switch (c = PyUnicode_READ_CHAR(self->str.str, self->str.start++)) {
case '{':
case '}':
markup_follows = 1;
break;
default:
continue;
}
break;
}
at_end = self->str.start >= self->str.end;
len = self->str.start - start;
if ((c == '}') && (at_end ||
(c != PyUnicode_READ_CHAR(self->str.str,
self->str.start)))) {
PyErr_SetString(PyExc_ValueError, "Single '}' encountered "
"in format string");
return 0;
}
if (at_end && c == '{') {
PyErr_SetString(PyExc_ValueError, "Single '{' encountered "
"in format string");
return 0;
}
if (!at_end) {
if (c == PyUnicode_READ_CHAR(self->str.str, self->str.start)) {
/* escaped } or {, skip it in the input. there is no
markup object following us, just this literal text */
self->str.start++;
markup_follows = 0;
}
else
len--;
}
/* record the literal text */
literal->str = self->str.str;
literal->start = start;
literal->end = start + len;
if (!markup_follows)
return 2;
/* this is markup; parse the field */
*field_present = 1;
if (!parse_field(&self->str, field_name, format_spec,
format_spec_needs_expanding, conversion))
return 0;
return 2;
}
/* do the !r or !s conversion on obj */
static PyObject *
do_conversion(PyObject *obj, Py_UCS4 conversion)
{
/* XXX in pre-3.0, do we need to convert this to unicode, since it
might have returned a string? */
switch (conversion) {
case 'r':
return PyObject_Repr(obj);
case 's':
return PyObject_Str(obj);
case 'a':
return PyObject_ASCII(obj);
default:
if (conversion > 32 && conversion < 127) {
/* It's the ASCII subrange; casting to char is safe
(assuming the execution character set is an ASCII
superset). */
PyErr_Format(PyExc_ValueError,
"Unknown conversion specifier %c",
(char)conversion);
} else
PyErr_Format(PyExc_ValueError,
"Unknown conversion specifier \\x%x",
(unsigned int)conversion);
return NULL;
}
}
/* given:
{field_name!conversion:format_spec}
compute the result and write it to output.
format_spec_needs_expanding is an optimization. if it's false,
just output the string directly, otherwise recursively expand the
format_spec string.
field_name is allowed to be zero length, in which case we
are doing auto field numbering.
*/
static int
output_markup(SubString *field_name, SubString *format_spec,
int format_spec_needs_expanding, Py_UCS4 conversion,
_PyUnicodeWriter *writer, PyObject *args, PyObject *kwargs,
int recursion_depth, AutoNumber *auto_number)
{
PyObject *tmp = NULL;
PyObject *fieldobj = NULL;
SubString expanded_format_spec;
SubString *actual_format_spec;
int result = 0;
/* convert field_name to an object */
fieldobj = get_field_object(field_name, args, kwargs, auto_number);
if (fieldobj == NULL)
goto done;
if (conversion != '\0') {
tmp = do_conversion(fieldobj, conversion);
if (tmp == NULL || PyUnicode_READY(tmp) == -1)
goto done;
/* do the assignment, transferring ownership: fieldobj = tmp */
Py_DECREF(fieldobj);
fieldobj = tmp;
tmp = NULL;
}
/* if needed, recurively compute the format_spec */
if (format_spec_needs_expanding) {
tmp = build_string(format_spec, args, kwargs, recursion_depth-1,
auto_number);
if (tmp == NULL || PyUnicode_READY(tmp) == -1)
goto done;
/* note that in the case we're expanding the format string,
tmp must be kept around until after the call to
render_field. */
SubString_init(&expanded_format_spec, tmp, 0, PyUnicode_GET_LENGTH(tmp));
actual_format_spec = &expanded_format_spec;
}
else
actual_format_spec = format_spec;
if (render_field(fieldobj, actual_format_spec, writer) == 0)
goto done;
result = 1;
done:
Py_XDECREF(fieldobj);
Py_XDECREF(tmp);
return result;
}
/*
do_markup is the top-level loop for the format() method. It
searches through the format string for escapes to markup codes, and
calls other functions to move non-markup text to the output,
and to perform the markup to the output.
*/
static int
do_markup(SubString *input, PyObject *args, PyObject *kwargs,
_PyUnicodeWriter *writer, int recursion_depth, AutoNumber *auto_number)
{
MarkupIterator iter;
int format_spec_needs_expanding;
int result;
int field_present;
SubString literal;
SubString field_name;
SubString format_spec;
Py_UCS4 conversion;
MarkupIterator_init(&iter, input->str, input->start, input->end);
while ((result = MarkupIterator_next(&iter, &literal, &field_present,
&field_name, &format_spec,
&conversion,
&format_spec_needs_expanding)) == 2) {
if (literal.end != literal.start) {
if (!field_present && iter.str.start == iter.str.end)
writer->overallocate = 0;
if (_PyUnicodeWriter_WriteSubstring(writer, literal.str,
literal.start, literal.end) < 0)
return 0;
}
if (field_present) {
if (iter.str.start == iter.str.end)
writer->overallocate = 0;
if (!output_markup(&field_name, &format_spec,
format_spec_needs_expanding, conversion, writer,
args, kwargs, recursion_depth, auto_number))
return 0;
}
}
return result;
}
/*
build_string allocates the output string and then
calls do_markup to do the heavy lifting.
*/
static PyObject *
build_string(SubString *input, PyObject *args, PyObject *kwargs,
int recursion_depth, AutoNumber *auto_number)
{
_PyUnicodeWriter writer;
/* check the recursion level */
if (recursion_depth <= 0) {
PyErr_SetString(PyExc_ValueError,
"Max string recursion exceeded");
return NULL;
}
_PyUnicodeWriter_Init(&writer);
writer.overallocate = 1;
writer.min_length = PyUnicode_GET_LENGTH(input->str) + 100;
if (!do_markup(input, args, kwargs, &writer, recursion_depth,
auto_number)) {
_PyUnicodeWriter_Dealloc(&writer);
return NULL;
}
return _PyUnicodeWriter_Finish(&writer);
}
/************************************************************************/
/*********** main routine ***********************************************/
/************************************************************************/
/* this is the main entry point */
static PyObject *
do_string_format(PyObject *self, PyObject *args, PyObject *kwargs)
{
SubString input;
/* PEP 3101 says only 2 levels, so that
"{0:{1}}".format('abc', 's') # works
"{0:{1:{2}}}".format('abc', 's', '') # fails
*/
int recursion_depth = 2;
AutoNumber auto_number;
if (PyUnicode_READY(self) == -1)
return NULL;
AutoNumber_Init(&auto_number);
SubString_init(&input, self, 0, PyUnicode_GET_LENGTH(self));
return build_string(&input, args, kwargs, recursion_depth, &auto_number);
}
static PyObject *
do_string_format_map(PyObject *self, PyObject *obj)
{
return do_string_format(self, NULL, obj);
}
/************************************************************************/
/*********** formatteriterator ******************************************/
/************************************************************************/
/* This is used to implement string.Formatter.vparse(). It exists so
Formatter can share code with the built in unicode.format() method.
It's really just a wrapper around MarkupIterator that is callable
from Python. */
typedef struct {
PyObject_HEAD
PyObject *str;
MarkupIterator it_markup;
} formatteriterobject;
static void
formatteriter_dealloc(formatteriterobject *it)
{
Py_XDECREF(it->str);
PyObject_FREE(it);
}
/* returns a tuple:
(literal, field_name, format_spec, conversion)
literal is any literal text to output. might be zero length
field_name is the string before the ':'. might be None
format_spec is the string after the ':'. mibht be None
conversion is either None, or the string after the '!'
*/
static PyObject *
formatteriter_next(formatteriterobject *it)
{
SubString literal;
SubString field_name;
SubString format_spec;
Py_UCS4 conversion;
int format_spec_needs_expanding;
int field_present;
int result = MarkupIterator_next(&it->it_markup, &literal, &field_present,
&field_name, &format_spec, &conversion,