2014-06-12 21:51:34 +00:00
|
|
|
/*
|
|
|
|
* This file is part of the Micro Python project, http://micropython.org/
|
|
|
|
*
|
|
|
|
* The MIT License (MIT)
|
|
|
|
*
|
|
|
|
* Copyright (c) 2013, 2014 Damien P. George
|
|
|
|
* Copyright (c) 2014 Paul Sokolovsky
|
|
|
|
*
|
|
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
|
|
* of this software and associated documentation files (the "Software"), to deal
|
|
|
|
* in the Software without restriction, including without limitation the rights
|
|
|
|
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
|
|
* copies of the Software, and to permit persons to whom the Software is
|
|
|
|
* furnished to do so, subject to the following conditions:
|
|
|
|
*
|
|
|
|
* The above copyright notice and this permission notice shall be included in
|
|
|
|
* all copies or substantial portions of the Software.
|
|
|
|
*
|
|
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
|
|
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
|
|
|
* THE SOFTWARE.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <string.h>
|
|
|
|
#include <assert.h>
|
|
|
|
|
2015-01-01 20:27:54 +00:00
|
|
|
#include "py/nlr.h"
|
|
|
|
#include "py/objstr.h"
|
|
|
|
#include "py/objlist.h"
|
|
|
|
#include "py/runtime0.h"
|
|
|
|
#include "py/runtime.h"
|
|
|
|
#include "py/pfenv.h"
|
2014-06-12 21:51:34 +00:00
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
#if MICROPY_PY_BUILTINS_STR_UNICODE
|
2014-06-12 21:51:34 +00:00
|
|
|
|
|
|
|
STATIC mp_obj_t mp_obj_new_str_iterator(mp_obj_t str);
|
|
|
|
|
|
|
|
/******************************************************************************/
|
|
|
|
/* str */
|
|
|
|
|
2014-06-13 20:00:15 +00:00
|
|
|
STATIC void uni_print_quoted(void (*print)(void *env, const char *fmt, ...), void *env, const byte *str_data, uint str_len) {
|
2014-06-12 21:51:34 +00:00
|
|
|
// this escapes characters, but it will be very slow to print (calling print many times)
|
|
|
|
bool has_single_quote = false;
|
|
|
|
bool has_double_quote = false;
|
|
|
|
for (const byte *s = str_data, *top = str_data + str_len; !has_double_quote && s < top; s++) {
|
|
|
|
if (*s == '\'') {
|
|
|
|
has_single_quote = true;
|
|
|
|
} else if (*s == '"') {
|
|
|
|
has_double_quote = true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
int quote_char = '\'';
|
|
|
|
if (has_single_quote && !has_double_quote) {
|
|
|
|
quote_char = '"';
|
|
|
|
}
|
|
|
|
print(env, "%c", quote_char);
|
2014-06-14 14:48:40 +00:00
|
|
|
const byte *s = str_data, *top = str_data + str_len;
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
while (s < top) {
|
|
|
|
unichar ch;
|
2014-06-13 20:00:15 +00:00
|
|
|
ch = utf8_get_char(s);
|
|
|
|
s = utf8_next_char(s);
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
if (ch == quote_char) {
|
2014-06-12 21:51:34 +00:00
|
|
|
print(env, "\\%c", quote_char);
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
} else if (ch == '\\') {
|
2014-06-12 21:51:34 +00:00
|
|
|
print(env, "\\\\");
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
} else if (32 <= ch && ch <= 126) {
|
|
|
|
print(env, "%c", ch);
|
|
|
|
} else if (ch == '\n') {
|
2014-06-12 21:51:34 +00:00
|
|
|
print(env, "\\n");
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
} else if (ch == '\r') {
|
2014-06-12 21:51:34 +00:00
|
|
|
print(env, "\\r");
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
} else if (ch == '\t') {
|
2014-06-12 21:51:34 +00:00
|
|
|
print(env, "\\t");
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
} else if (ch < 0x100) {
|
|
|
|
print(env, "\\x%02x", ch);
|
|
|
|
} else if (ch < 0x10000) {
|
|
|
|
print(env, "\\u%04x", ch);
|
2014-06-12 21:51:34 +00:00
|
|
|
} else {
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
print(env, "\\U%08x", ch);
|
2014-06-12 21:51:34 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
print(env, "%c", quote_char);
|
|
|
|
}
|
|
|
|
|
2014-06-13 20:00:15 +00:00
|
|
|
STATIC void uni_print(void (*print)(void *env, const char *fmt, ...), void *env, mp_obj_t self_in, mp_print_kind_t kind) {
|
2014-06-12 21:51:34 +00:00
|
|
|
GET_STR_DATA_LEN(self_in, str_data, str_len);
|
2014-09-17 21:56:34 +00:00
|
|
|
#if MICROPY_PY_UJSON
|
|
|
|
if (kind == PRINT_JSON) {
|
2014-09-25 16:35:56 +00:00
|
|
|
mp_str_print_json(print, env, str_data, str_len);
|
2014-09-17 21:56:34 +00:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
#endif
|
2014-06-13 20:00:15 +00:00
|
|
|
if (kind == PRINT_STR) {
|
2014-06-12 21:51:34 +00:00
|
|
|
print(env, "%.*s", str_len, str_data);
|
|
|
|
} else {
|
2014-06-13 20:00:15 +00:00
|
|
|
uni_print_quoted(print, env, str_data, str_len);
|
2014-06-12 21:51:34 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-08-29 23:35:11 +00:00
|
|
|
STATIC mp_obj_t uni_unary_op(mp_uint_t op, mp_obj_t self_in) {
|
2014-06-13 20:37:18 +00:00
|
|
|
GET_STR_DATA_LEN(self_in, str_data, str_len);
|
|
|
|
switch (op) {
|
|
|
|
case MP_UNARY_OP_BOOL:
|
|
|
|
return MP_BOOL(str_len != 0);
|
|
|
|
case MP_UNARY_OP_LEN:
|
2014-06-28 20:14:30 +00:00
|
|
|
return MP_OBJ_NEW_SMALL_INT(unichar_charlen((const char *)str_data, str_len));
|
2014-06-13 20:37:18 +00:00
|
|
|
default:
|
|
|
|
return MP_OBJ_NULL; // op not supported
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-08-29 23:35:11 +00:00
|
|
|
STATIC mp_obj_t str_make_new(mp_obj_t type_in, mp_uint_t n_args, mp_uint_t n_kw, const mp_obj_t *args) {
|
2014-06-12 21:51:34 +00:00
|
|
|
#if MICROPY_CPYTHON_COMPAT
|
|
|
|
if (n_kw != 0) {
|
|
|
|
mp_arg_error_unimpl_kw();
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
switch (n_args) {
|
|
|
|
case 0:
|
|
|
|
return MP_OBJ_NEW_QSTR(MP_QSTR_);
|
|
|
|
|
|
|
|
case 1:
|
|
|
|
{
|
|
|
|
vstr_t *vstr = vstr_new();
|
|
|
|
mp_obj_print_helper((void (*)(void*, const char*, ...))vstr_printf, vstr, args[0], PRINT_STR);
|
|
|
|
mp_obj_t s = mp_obj_new_str(vstr->buf, vstr->len, false);
|
|
|
|
vstr_free(vstr);
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
case 2:
|
|
|
|
case 3:
|
|
|
|
{
|
|
|
|
// TODO: validate 2nd/3rd args
|
2014-10-30 21:58:08 +00:00
|
|
|
if (MP_OBJ_IS_TYPE(args[0], &mp_type_bytes)) {
|
|
|
|
GET_STR_DATA_LEN(args[0], str_data, str_len);
|
|
|
|
GET_STR_HASH(args[0], str_hash);
|
|
|
|
mp_obj_str_t *o = mp_obj_new_str_of_type(&mp_type_str, NULL, str_len);
|
|
|
|
o->data = str_data;
|
|
|
|
o->hash = str_hash;
|
|
|
|
return o;
|
|
|
|
} else {
|
|
|
|
mp_buffer_info_t bufinfo;
|
|
|
|
mp_get_buffer_raise(args[0], &bufinfo, MP_BUFFER_READ);
|
|
|
|
return mp_obj_new_str(bufinfo.buf, bufinfo.len, false);
|
2014-06-12 21:51:34 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
default:
|
|
|
|
nlr_raise(mp_obj_new_exception_msg(&mp_type_TypeError, "str takes at most 3 arguments"));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
// Convert an index into a pointer to its lead byte. Out of bounds indexing will raise IndexError or
|
|
|
|
// be capped to the first/last character of the string, depending on is_slice.
|
2014-08-30 13:59:21 +00:00
|
|
|
const byte *str_index_to_ptr(const mp_obj_type_t *type, const byte *self_data, mp_uint_t self_len,
|
2014-06-14 21:35:09 +00:00
|
|
|
mp_obj_t index, bool is_slice) {
|
2014-07-03 12:25:24 +00:00
|
|
|
mp_int_t i;
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
// Copied from mp_get_index; I don't want bounds checking, just give me
|
|
|
|
// the integer as-is. (I can't bounds-check without scanning the whole
|
|
|
|
// string; an out-of-bounds index will be caught in the loops below.)
|
|
|
|
if (MP_OBJ_IS_SMALL_INT(index)) {
|
|
|
|
i = MP_OBJ_SMALL_INT_VALUE(index);
|
|
|
|
} else if (!mp_obj_get_int_maybe(index, &i)) {
|
|
|
|
nlr_raise(mp_obj_new_exception_msg_varg(&mp_type_TypeError, "string indices must be integers, not %s", mp_obj_get_type_str(index)));
|
|
|
|
}
|
2014-06-14 21:35:09 +00:00
|
|
|
const byte *s, *top = self_data + self_len;
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
if (i < 0)
|
|
|
|
{
|
|
|
|
// Negative indexing is performed by counting from the end of the string.
|
|
|
|
for (s = top - 1; i; --s) {
|
|
|
|
if (s < self_data) {
|
|
|
|
if (is_slice) {
|
|
|
|
return self_data;
|
|
|
|
}
|
|
|
|
nlr_raise(mp_obj_new_exception_msg_varg(&mp_type_IndexError, "string index out of range"));
|
|
|
|
}
|
|
|
|
if (!UTF8_IS_CONT(*s)) {
|
|
|
|
++i;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
++s;
|
|
|
|
} else if (!i) {
|
|
|
|
return self_data; // Shortcut - str[0] is its base pointer
|
|
|
|
} else {
|
|
|
|
// Positive indexing, correspondingly, counts from the start of the string.
|
|
|
|
// It's assumed that negative indexing will generally be used with small
|
|
|
|
// absolute values (eg str[-1], not str[-1000000]), which means it'll be
|
|
|
|
// more efficient this way.
|
|
|
|
for (s = self_data; true; ++s) {
|
|
|
|
if (s >= top) {
|
|
|
|
if (is_slice) {
|
|
|
|
return top;
|
|
|
|
}
|
|
|
|
nlr_raise(mp_obj_new_exception_msg_varg(&mp_type_IndexError, "string index out of range"));
|
|
|
|
}
|
|
|
|
while (UTF8_IS_CONT(*s)) {
|
|
|
|
++s;
|
|
|
|
}
|
|
|
|
if (!i--) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
2014-06-12 21:51:34 +00:00
|
|
|
STATIC mp_obj_t str_subscr(mp_obj_t self_in, mp_obj_t index, mp_obj_t value) {
|
|
|
|
mp_obj_type_t *type = mp_obj_get_type(self_in);
|
|
|
|
GET_STR_DATA_LEN(self_in, self_data, self_len);
|
|
|
|
if (value == MP_OBJ_SENTINEL) {
|
|
|
|
// load
|
|
|
|
#if MICROPY_PY_BUILTINS_SLICE
|
|
|
|
if (MP_OBJ_IS_TYPE(index, &mp_type_slice)) {
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
mp_obj_t ostart, ostop, ostep;
|
|
|
|
mp_obj_slice_get(index, &ostart, &ostop, &ostep);
|
|
|
|
if (ostep != mp_const_none && ostep != MP_OBJ_NEW_SMALL_INT(1)) {
|
2014-06-12 21:51:34 +00:00
|
|
|
nlr_raise(mp_obj_new_exception_msg(&mp_type_NotImplementedError,
|
|
|
|
"only slices with step=1 (aka None) are supported"));
|
|
|
|
}
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
|
|
|
|
if (type == &mp_type_bytes) {
|
2014-07-03 12:25:24 +00:00
|
|
|
mp_int_t start = 0, stop = self_len;
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
if (ostart != mp_const_none) {
|
|
|
|
start = MP_OBJ_SMALL_INT_VALUE(ostart);
|
|
|
|
if (start < 0) {
|
|
|
|
start = self_len + start;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (ostop != mp_const_none) {
|
|
|
|
stop = MP_OBJ_SMALL_INT_VALUE(ostop);
|
|
|
|
if (stop < 0) {
|
|
|
|
stop = self_len + stop;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return mp_obj_new_str_of_type(type, self_data + start, stop - start);
|
|
|
|
}
|
2014-06-14 21:35:09 +00:00
|
|
|
const byte *pstart, *pstop;
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
if (ostart != mp_const_none) {
|
2014-06-14 21:35:09 +00:00
|
|
|
pstart = str_index_to_ptr(type, self_data, self_len, ostart, true);
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
} else {
|
2014-06-14 21:35:09 +00:00
|
|
|
pstart = self_data;
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
}
|
|
|
|
if (ostop != mp_const_none) {
|
|
|
|
// pstop will point just after the stop character. This depends on
|
|
|
|
// the \0 at the end of the string.
|
2014-06-14 21:35:09 +00:00
|
|
|
pstop = str_index_to_ptr(type, self_data, self_len, ostop, true);
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
} else {
|
2014-06-14 21:35:09 +00:00
|
|
|
pstop = self_data + self_len;
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
}
|
|
|
|
if (pstop < pstart) {
|
|
|
|
return MP_OBJ_NEW_QSTR(MP_QSTR_);
|
|
|
|
}
|
|
|
|
return mp_obj_new_str_of_type(type, (const byte *)pstart, pstop - pstart);
|
2014-06-12 21:51:34 +00:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
if (type == &mp_type_bytes) {
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
uint index_val = mp_get_index(type, self_len, index, false);
|
2014-07-31 09:49:14 +00:00
|
|
|
return MP_OBJ_NEW_SMALL_INT(self_data[index_val]);
|
2014-06-12 21:51:34 +00:00
|
|
|
}
|
2014-06-14 21:35:09 +00:00
|
|
|
const byte *s = str_index_to_ptr(type, self_data, self_len, index, false);
|
objstrunicode: Basic implementation of unicode handling.
Squashed commit of the following:
commit 99dc21b67a895dc10d3c846bc158d27c839cee48
Author: Chris Angelico <rosuav@gmail.com>
Date: Thu Jun 12 02:18:54 2014 +1000
Optimize as per TODO (thanks Damien!)
commit 5bf0153ecad8348443058d449d74504fc458fe51
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 08:42:06 2014 +1000
Test a default (= UTF-8) encode and decode
commit c962057ac340832c4fde60896f656a3fe3ad78a9
Merge: e2c9782 195de32
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:23:03 2014 +1000
Merge branch 'master' into unicode, resolving conflict on py/obj.h
commit e2c9782a65eb57f481d441d40161de427e1940ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:05:57 2014 +1000
More whitespace fixups
commit 086a2a0f57afbc1f731697fd5d3a0cbbb80e5418
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 05:04:20 2014 +1000
Properly implement string slicing
commit 0d339a143e2b6442366145e7f3d64aada293eaa0
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:24:11 2014 +1000
Support slicing in str_index_to_ptr, and fix a bounds error
commit 24371c7267d360e77cf5eabc2e8ce9a73d2ee0da
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:10:22 2014 +1000
Break out index-to-pointer calculation into a function
commit 616c24ac014c3ca56008428c506034dd1bfff7a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 02:03:11 2014 +1000
Add tests of string slicing, which currently fail
commit a24d19f676fe8cc21dad512d91b826892e162a5b
Author: Chris Angelico <rosuav@gmail.com>
Date: Tue Jun 10 01:56:53 2014 +1000
Change string indexing to not precalculate the charlen, and add test for neg indexing
commit 0bcc7ab89eafb2ae53195e94c9bea42a4e886b64
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 22:09:17 2014 +1000
Clean up constant qstr declarations now that charlen isn't needed
commit 5473e1a1dba2124b7b0c207f2964293cfbe80167
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:18:42 2014 +1000
Remove the charlen field from strings, calculating it when required
commit 5c1658ec71aefbdc88c261ce2e57dc7670cdc6ef
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 07:11:27 2014 +1000
Get rid of mp_obj_str_get_data_len() which was used in only one place
commit a019ba968b4e8daf7f3674f63c5cc400e304c509
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:58:26 2014 +1000
Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes
commit 44b0d5cff846ba487c526ed95be1b3d1cd3d762a
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:32:44 2014 +1000
Use utf8_get/next_char in building up a string's repr
commit 30d1bad33f7af90f1971987c39864c8fcf3f5c21
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 06:10:45 2014 +1000
Make utf8_get_char() and utf8_next_char() actually do what their names say
commit bc990dad9afb8ec112f5e7f7f79d5ab415da0e72
Author: Chris Angelico <rosuav@gmail.com>
Date: Sun Jun 8 02:10:59 2014 +1000
Revert "Add PEP 393-flags to strings and stub usage."
This reverts commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba.
commit f9bebb28ad52467f2f2d7a752bb033296b6c2f9b
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:41:48 2014 +1000
Whitespace fixes
commit 279de0c8eb3cb186914799ccc5ee94ea97f56de4
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 15:28:35 2014 +1000
Formatting/layout improvements - introduce macros for UTF-8 byte detection, add braces. No functional changes.
commit f1911f53d56da809c97b07245f5728a419e8fb30
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:56:02 2014 +1000
Make chr() Unicode-aware
commit f51ad737b48ac04c161197a4012821d50885c4c7
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:44:07 2014 +1000
Make a string's repr Unicode-aware
commit 01bd68684611585d437982dccdf05b33cbedc630
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:33:43 2014 +1000
Expand the Unicode tests
commit 7bc91904f899f8012089fc14a06495680a51e590
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:27:30 2014 +1000
Record byte lengths for byte strings
commit bb132120717cf176dcfb26f87fa309378f76ab5f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 11:25:06 2014 +1000
Make ord() Unicode-aware
commit 03f0cbe9051b62192be97b59f84f63f9216668bf
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 10:24:35 2014 +1000
Retain characters as UTF-8 encoded Unicode
commit e924659b85c001916a5ff7f4d1d8b3ebe2bf0c2f
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 08:37:27 2014 +1000
Add support for \u and \U escapes, but not \N (with explanatory comment)
commit 231031ac5f0346e4ffcf9c4abec2bd33f566232c
Author: Chris Angelico <rosuav@gmail.com>
Date: Sat Jun 7 05:09:35 2014 +1000
Add character length to qstr
commit 6df1b946fb17d8d5df3d91b21cde627c3d4556a8
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:48:36 2014 +1000
Add test of UTF-8 encoded source file resulting in properly formed string
commit 16429b81a8483cf25865ed11afd81a7d9c253c26
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:44:15 2014 +1000
Make len(s) return character length (even though creation's still buggy)
commit cd2cf6663cc47831dbc97819ad5c50ad33f939d3
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:36 2014 +1000
HACK - When indexing a qstr, count its charlen. Stupidly inefficient but POC.
All tests pass now, though string creation is still buggy.
commit 47c234584d3358dfa6b4003d5e7264105d17b8f7
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 13:15:32 2014 +1000
objstr: Record character length separately from byte length
CAUTION: Buggy, may crash stuff - qstr needs equivalent functionality too
commit b0f41c72af27d3b361027146025877b3d7e8785c
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:37:36 2014 +1000
Beginnings of UTF-8 support - construct strings from that many UTF-8-encoded chars, and subscript bytes the same way
commit 89452be641674601e9bfce86dc71c17c3140a6cf
Author: Chris Angelico <rosuav@gmail.com>
Date: Fri Jun 6 05:28:47 2014 +1000
Update comments - now aiming for UTF-8 rather than PEP 393 strings
commit c239f509521d1a0f9563bf9c5de0c4fb9a6a33ba
Author: Chris Angelico <rosuav@gmail.com>
Date: Wed Jun 4 05:28:12 2014 +1000
Add PEP 393-flags to strings and stub usage.
The test suite all passes, but nothing has actually been changed.
2014-06-03 19:28:12 +00:00
|
|
|
int len = 1;
|
|
|
|
if (UTF8_IS_NONASCII(*s)) {
|
|
|
|
// Count the number of 1 bits (after the first)
|
|
|
|
for (char mask = 0x40; *s & mask; mask >>= 1) {
|
|
|
|
++len;
|
|
|
|
}
|
|
|
|
}
|
2014-06-14 21:35:09 +00:00
|
|
|
return mp_obj_new_str((const char*)s, len, true); // This will create a one-character string
|
2014-06-12 21:51:34 +00:00
|
|
|
} else {
|
|
|
|
return MP_OBJ_NULL; // op not supported
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
STATIC const mp_map_elem_t str_locals_dict_table[] = {
|
|
|
|
#if MICROPY_CPYTHON_COMPAT
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_encode), (mp_obj_t)&str_encode_obj },
|
|
|
|
#endif
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_find), (mp_obj_t)&str_find_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_rfind), (mp_obj_t)&str_rfind_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_index), (mp_obj_t)&str_index_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_rindex), (mp_obj_t)&str_rindex_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_join), (mp_obj_t)&str_join_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_split), (mp_obj_t)&str_split_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_rsplit), (mp_obj_t)&str_rsplit_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_startswith), (mp_obj_t)&str_startswith_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_endswith), (mp_obj_t)&str_endswith_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_strip), (mp_obj_t)&str_strip_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_lstrip), (mp_obj_t)&str_lstrip_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_rstrip), (mp_obj_t)&str_rstrip_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_format), (mp_obj_t)&str_format_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_replace), (mp_obj_t)&str_replace_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_count), (mp_obj_t)&str_count_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_partition), (mp_obj_t)&str_partition_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_rpartition), (mp_obj_t)&str_rpartition_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_lower), (mp_obj_t)&str_lower_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_upper), (mp_obj_t)&str_upper_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_isspace), (mp_obj_t)&str_isspace_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_isalpha), (mp_obj_t)&str_isalpha_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_isdigit), (mp_obj_t)&str_isdigit_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_isupper), (mp_obj_t)&str_isupper_obj },
|
|
|
|
{ MP_OBJ_NEW_QSTR(MP_QSTR_islower), (mp_obj_t)&str_islower_obj },
|
|
|
|
};
|
2014-06-12 21:51:34 +00:00
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
STATIC MP_DEFINE_CONST_DICT(str_locals_dict, str_locals_dict_table);
|
2014-06-12 21:51:34 +00:00
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
const mp_obj_type_t mp_type_str = {
|
|
|
|
{ &mp_type_type },
|
|
|
|
.name = MP_QSTR_str,
|
2014-06-13 20:00:15 +00:00
|
|
|
.print = uni_print,
|
2014-06-13 19:01:26 +00:00
|
|
|
.make_new = str_make_new,
|
2014-06-13 20:37:18 +00:00
|
|
|
.unary_op = uni_unary_op,
|
2014-06-28 09:27:23 +00:00
|
|
|
.binary_op = mp_obj_str_binary_op,
|
2014-06-13 19:01:26 +00:00
|
|
|
.subscr = str_subscr,
|
|
|
|
.getiter = mp_obj_new_str_iterator,
|
2014-06-28 09:27:23 +00:00
|
|
|
.buffer_p = { .get_buffer = mp_obj_str_get_buffer },
|
2014-06-13 19:01:26 +00:00
|
|
|
.locals_dict = (mp_obj_t)&str_locals_dict,
|
|
|
|
};
|
2014-06-12 21:51:34 +00:00
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
/******************************************************************************/
|
|
|
|
/* str iterator */
|
2014-06-12 21:51:34 +00:00
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
typedef struct _mp_obj_str_it_t {
|
|
|
|
mp_obj_base_t base;
|
|
|
|
mp_obj_t str;
|
2014-07-03 12:25:24 +00:00
|
|
|
mp_uint_t cur;
|
2014-06-13 19:01:26 +00:00
|
|
|
} mp_obj_str_it_t;
|
2014-06-12 21:51:34 +00:00
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
STATIC mp_obj_t str_it_iternext(mp_obj_t self_in) {
|
|
|
|
mp_obj_str_it_t *self = self_in;
|
|
|
|
GET_STR_DATA_LEN(self->str, str, len);
|
|
|
|
if (self->cur < len) {
|
2014-06-13 23:07:25 +00:00
|
|
|
const byte *cur = str + self->cur;
|
|
|
|
const byte *end = utf8_next_char(str + self->cur);
|
|
|
|
mp_obj_t o_out = mp_obj_new_str((const char*)cur, end - cur, true);
|
|
|
|
self->cur += end - cur;
|
2014-06-13 19:01:26 +00:00
|
|
|
return o_out;
|
2014-06-12 21:51:34 +00:00
|
|
|
} else {
|
2014-06-13 19:01:26 +00:00
|
|
|
return MP_OBJ_STOP_ITERATION;
|
2014-06-12 21:51:34 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
STATIC const mp_obj_type_t mp_type_str_it = {
|
|
|
|
{ &mp_type_type },
|
|
|
|
.name = MP_QSTR_iterator,
|
|
|
|
.getiter = mp_identity,
|
|
|
|
.iternext = str_it_iternext,
|
|
|
|
};
|
2014-06-12 21:51:34 +00:00
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
mp_obj_t mp_obj_new_str_iterator(mp_obj_t str) {
|
|
|
|
mp_obj_str_it_t *o = m_new_obj(mp_obj_str_it_t);
|
|
|
|
o->base.type = &mp_type_str_it;
|
|
|
|
o->str = str;
|
|
|
|
o->cur = 0;
|
|
|
|
return o;
|
2014-06-12 21:51:34 +00:00
|
|
|
}
|
|
|
|
|
2014-06-13 19:01:26 +00:00
|
|
|
#endif // MICROPY_PY_BUILTINS_STR_UNICODE
|