642132920f
Fixing performance regression caused by helpful code contributions
...
that moved inlineable functions into the source file combined with
helpful compilers which aren't smart enough to do the inlinining in
any case.
2019-05-31 18:16:12 -04:00
8526387acb
Improving error codes. ( #176 )
...
* This commit adds new error codes.
2019-05-24 17:28:56 -04:00
17ac5c0525
This adds guards so that we can better detect the case where we have neither AVX2 nor ARM NEON. ( #173 )
2019-05-24 17:26:29 -04:00
43dba8ac7f
A slightly better "flatten"? ( #166 )
...
* This seems beneficial.
2019-05-19 12:33:45 -04:00
dcd0cb8080
Fix for https://github.com/lemire/simdjson/issues/58 ( #168 )
2019-05-19 12:25:27 -04:00
47beaff152
Adding white-listing for memory sanitizer.
2019-05-19 11:18:54 -04:00
f75280ac9c
Fix for issue 150 ( #162 )
...
* Checks for issue 150. We run through the test files with sanitizers on.
* Fix for issue 150: the remaining issues were an overrun on the depth capacity and an "off-by-1" overrun on tape capacity.
* Improving makefile.
* Safer git submodule command.
* Getting get 'git' on circleci
2019-05-09 20:51:33 -04:00
e370a65383
Fix for issues 32, 50, 131, 137
...
* Improving portability.
* Revisiting faulty logic regarding same-page overruns.
* Disabling same-page overruns under VS.
* Clarifying the documentation
* Fix for issue 131 + being more explicit regarding memory realloc.
* Fix for issue 137.
* removing "using namespace std" throughout. Fix for 50
* Introducing typed malloc/free.
* Introducing a custom class (padded_string) that solves several minor usability issues.
* Updating amalgamation for testing.
2019-05-09 17:59:51 -04:00
20cda07eef
Minor grammatical thing ("an integer" vs "a integer")
2019-05-09 10:48:31 -04:00
c1975166a0
False atom fix ( #156 )
...
* Add failing test for falsy atom
* Fix false atom parsing
2019-05-09 10:45:42 -04:00
f0574d492c
Fix for issue 154 ( #157 )
...
* Changes necessary to reproduce
https://github.com/lemire/simdjson/issues/154
* Fixing issue 154.
2019-05-08 22:33:11 -04:00
6f0d350f2c
Fix to issue #148 . ( #151 )
...
* Issue #148 fix.
* Test cases for issue #148 .
2019-05-07 20:56:36 -04:00
719dff1312
Add predicates to ParsedJson::iterator ( #153 )
2019-05-07 14:11:33 -04:00
681cd33698
Making the iterator a tad safer (tweaking the constructor so that it can throw).
2019-04-22 10:53:25 -04:00
1153778f92
fix a bug in copy constructor of ParsedJson::iterator. ( #146 )
2019-04-22 10:37:02 -04:00
0250352139
Merge branch 'master' of https://github.com/lemire/simdjson
2019-04-01 02:08:15 -04:00
134ba8d1dd
Ratty version of transposed ARM SIMD stuff. Needs cleanup.
2019-04-01 02:07:38 -04:00
777b9c9a9e
Unbreak x86. Durp.
2019-03-30 15:50:35 +11:00
5ba29122fd
First cut of ARM port. Needs hand-hacked Makefile.
2019-03-30 00:47:35 -04:00
b4c815a60c
Concentrate and encapsulate SIMD use somewhat in preparation for ARM port.
2019-03-21 15:15:41 +11:00
473ab12a0a
Stage 2 doesn't need to know about intrinsics either (for itself)
2019-03-21 11:41:15 +11:00
df8f792183
Store the string lengths on the string tape ( #101 )
...
* Store string length in the string-tape item.
* Files are now limited to 4GB.
* Moving detection of unescaped chars to stage 1 to reduce the burden due to string parsing.
Fixes https://github.com/lemire/simdjson/issues/114
Fixes https://github.com/lemire/simdjson/issues/87
2019-03-13 19:32:57 -04:00
21eef55907
Changes to the behaviour of move_forward to make it suitable for iteration. ( Closes #73 ) ( #103 )
2019-03-06 12:13:55 -05:00
d873ee9983
Reuse aligned_malloc ( #108 )
2019-03-06 10:12:55 -05:00
6628c365c9
Substantial refactor (and clang-format google stype) of stage1_find_marks.cpp
2019-03-06 11:09:50 +11:00
2851ea490c
Export CMake targets ( #96 )
2019-03-04 16:07:06 -05:00
352dd5e7fa
Change parse_json return type from bool to int ( #82 )
...
* Added simdjerr namespace
* Updated jsonparser files
* updated stage1 and stage2
* removed stage2 inline function
* Added forgotten return statements
* Updated tools and benchmarks
* Corrected parenthesis
* Removed extra =
* Accidentally undid reinterpret_cast
* Better comments, undid a header name fuckup
* Added an errorMsg method, updated readme
* Removed useless header from stage2
* Updated single-header file
* added simdjerr.cpp contents to simdjson.cpp
* Made single header version work
* Updated singleheader test, fixed simdjson.cpp
* Renamed simdjerr namespace and files to simdjson
* Updating the amalgamation.
2019-03-02 17:18:45 -05:00
0c8ee105b4
fix memory free ( #86 )
2019-02-27 07:50:20 -05:00
a22c20fab0
Removed innecesary check and objects release. ( #79 )
2019-02-26 19:08:13 -05:00
3d48628e71
CMake: Add version and soversion to library target properties. ( #76 )
2019-02-26 16:39:59 -05:00
33341b60d8
Apply code review suggestions
...
- Undo explicit bool conversion
- Don't check for NULL before deleting pointer
2019-02-26 09:36:28 +01:00
e7683820d5
Merge branch 'master' into fix_minor_problems
2019-02-25 21:05:29 +01:00
7830b1be87
Use nothrow ( #65 )
...
* Use C++11 features
* Use std::nothrow
By default new throws std::bad_alloc, so no check code would be executed.
2019-02-25 14:36:45 -05:00
b521719b6f
Fix old-style C-Casts
2019-02-23 17:31:38 +01:00
ff22e75f95
Apply minor readability fixes
2019-02-23 17:28:20 +01:00
3d30fd5440
Fixed a stage number message and we now fail out if no structural chars from stage 1
2019-02-23 10:51:45 +11:00
389f8b514e
Porting recently introduced fix.
2019-02-22 14:39:21 -05:00
9606343b2c
ParsedJson & ParsedJson::iterator definitions in .cpp files ( #47 )
...
* Minor change to benchmark cmake
* Moved ParsedJson and its Iterator to separate .cpp files
* Uncommented functions, that has nothing to do with this pr
* Removed really_inline comments
* Reinstated some inline functions to restore previous performance
* Re-merged iterator in ParsedJson
* Uncommented some WARN_UNUSED
2019-02-22 14:38:35 -05:00
35eceaf1c4
Merge branch 'master' of github.com:lemire/simdjson
2019-01-24 14:29:02 -05:00
2ca29edab3
Fixing bad spacing.
2019-01-23 20:36:23 -05:00
85d8c9dbf0
Minor code cleaning
2019-01-18 15:21:54 -05:00
084dfbc2b3
Fix for name change.
2019-01-16 11:29:52 -05:00
ca5f3349e6
Removing useless macro.
2019-01-08 10:34:21 -05:00
bad32be5f6
Merge branch 'stage12unified_attempt2'
2018-12-31 17:33:01 -05:00
3ce1dd8087
Cleaning.
2018-12-31 17:13:32 -05:00
d7d568ee89
Trying something else.
2018-12-31 16:25:37 -05:00
3a2f746602
Trying with just a unified stage 3.
2018-12-31 14:03:43 -05:00
0317287071
Minor fix
2018-12-31 11:59:12 -05:00
58d41923fd
Porting to visual studio
...
Now builds on Visual Studio
2018-12-30 21:00:19 -05:00
386bebb33b
adding support for cmake.
2018-12-28 13:13:10 -05:00
3b24ba9043
Adding cmake
2018-12-28 13:05:42 -05:00
46ef59c679
Cleaning.
2018-12-27 20:19:10 -05:00
bf4089b33b
Removing custom types (more standard code).
2018-12-27 20:09:25 -05:00
20133963bc
Trying a detailed analysis.
2018-12-19 21:23:37 -05:00
0a109508de
Added documentation of the tape format.
2018-12-18 15:09:27 -05:00
779ce184fb
Getting ready to document the tape format.
2018-12-18 14:21:22 -05:00
e8d3d784ab
More fixing.
2018-12-10 22:21:03 -05:00
058eb917d1
Better doc.
2018-12-10 22:00:16 -05:00
e4703a383b
Even safer.
2018-12-10 20:54:31 -05:00
8a2281269c
Cleaning memset amd adding more tests.
2018-12-10 19:20:52 -05:00
7296d4d48b
Fixing...
2018-12-10 17:39:19 -05:00
05636f3a1d
Cleaning.
2018-12-10 16:47:02 -05:00
176d2ccda4
Tweaking.
2018-12-10 14:25:49 -05:00
9df22452af
First API implementation.
2018-12-07 22:19:57 -05:00
c2913d5d69
Adding dynamic memory allocation.
2018-12-06 21:44:26 -05:00
e2d2d2f8ff
Adding more tests.
2018-12-06 17:22:22 -05:00
e3a4b41c2e
Cleaning.
2018-11-30 22:02:32 -05:00
c11eefca32
More cleaning.
2018-11-30 21:31:05 -05:00
0e4804137c
It still works.
2018-11-30 20:36:56 -05:00
a8b99984f2
Intermediate step.
2018-11-30 20:27:16 -05:00
e5707331e9
Some refactoring.
2018-11-30 09:37:57 -05:00
12b518578d
Ok, the new code seems quite fast.
2018-11-29 22:15:02 -05:00
ce85dd0c3a
Still need to streamline number parsing.
2018-11-29 17:56:17 -05:00
c1de7662c1
Simplifying function call.
2018-11-28 11:12:28 -05:00
c1805783fc
Tweaking performance.
2018-11-27 21:13:31 -05:00
8648c4108e
MOre cleaning.
2018-11-27 20:42:35 -05:00
58ac242770
Ok. Let us benchmark this thing.
2018-11-27 15:05:50 -05:00
a43b0772e1
Lots and lots of cleaning.
2018-11-27 14:37:59 -05:00
5fae7b2100
Still working
2018-11-27 10:10:39 -05:00
50defa510f
Stupid work.
2018-11-26 16:55:24 -05:00
86a75462c5
Adding the ability of doing a dump.
2018-11-23 22:20:57 -05:00
17f5d0517d
Opting for a more common intrinsic.
2018-11-09 21:41:15 -05:00
76074a821f
Various cleaning steps.
2018-11-09 21:31:14 -05:00
0e5b939568
Merge branch 'master' of github.com:lemire/simdjson
2018-11-09 15:16:25 -05:00
c1a7e79862
Lifting the mem limit. (Dirty commit.)
2018-11-09 15:16:05 -05:00
df65de4ae2
Tuning presentation and fixing a problem with minifier benchmark.
2018-10-23 21:36:32 -04:00
8315f4c888
Cleaning up the code.
2018-10-17 21:31:22 -04:00
35381279c3
Maybe we can do away with the fast ASCII trick.
2018-10-17 21:05:38 -04:00
e517414080
We include character-encoding validation.
2018-10-17 19:22:09 -04:00
9fc8d8444b
We want to allow more than just arrays and objects, as per the JSON spec.
2018-10-17 13:57:42 -04:00
2ad9891b66
I think NO_PDEP_PLEASE should be defined by default. It seems
...
to be generally better/faster. More instructions, but also
more instructions per cycle, so it ends up being a net win.
2018-10-03 21:42:27 -04:00
ceb55cc8db
Pick new number parser as winner; move string parsing to own header
2018-09-28 14:27:48 +10:00
e4094afe08
Moving toward having number-parsing testing.
2018-09-27 17:38:15 -04:00
1c8339297d
With new number parser (faster!). Removing the dependency on the doubleconv library (which proves to be useless).
2018-09-26 23:35:33 -04:00
6239b9c13e
Overallocation
2018-09-26 14:20:28 -04:00
9f91650e72
Remove old 4-stage path.
2018-09-26 15:22:55 +10:00
b9706d462c
Minor cleanups.
2018-09-26 15:09:54 +10:00
36fadde3c7
Minor twiddles.
2018-09-26 13:52:05 +10:00
0d5797a827
Wrap the tape dump in debug code.
2018-09-26 13:28:16 +10:00
e9586b6b4d
Very first char is considered to follow "whitespace" for pseudo-structural character detection purposes
2018-09-26 13:27:39 +10:00
35503f1d8f
Oops noisy.
2018-09-26 13:21:05 +10:00
fa6c8990ff
Added a terrifying hack to append a idx-to-0-char to stage 2 output.
2018-09-26 13:20:08 +10:00
682c224d1a
Merge branch 'master' of https://github.com/lemire/simdjson
2018-09-26 11:29:23 +10:00
b0c05c03cc
Fix linkage between call sites and headers, add dump code, cleanup
2018-09-26 11:28:22 +10:00
dee1bbe54e
Integrating the new 3-stage approach.
2018-09-25 17:26:58 -04:00
555926849d
Bug cleanup (many vestiges of old 32-bit tape stil there) and more encapsulation of tapes.
2018-09-25 16:24:39 +10:00
8b2d00a337
Bug fix for ,] issue and cleanup.
2018-09-25 15:35:17 +10:00
64d07cd04c
Fix bug where strings were not parsed on 2nd and subsequent key:value pairs.
2018-09-24 15:16:22 +10:00
77bfe6c984
Fix some bad messages and the failure to parse key strings.
2018-09-24 10:54:29 +10:00
2a46b40457
Adding new stage34, a more straightforward replacement for stage 3 and 4 using a DFA and explicit stack
2018-09-24 10:44:05 +10:00
01f191e5eb
Merge branch 'master' of https://github.com/lemire/simdjson
2018-09-24 10:43:10 +10:00
053f04b15d
Crude first cut of "stage34", a unified code-based DFA with explicit stack for stages 3 and 4.
2018-09-24 10:42:30 +10:00
9d4f9e46f9
Some comments.
2018-09-16 16:40:59 -04:00
2aa6b93a02
Using a naive strtoll
2018-08-28 22:37:11 -04:00
0b2f9747f8
Check that numbers starting with 0 are followed by decimal, e, E or
...
they just end the number (0). Note that we allow -0. I guess.
2018-08-28 20:41:55 -04:00
e104c020ef
Versions of the code that use Google DoubleConv.
2018-08-24 20:49:45 -04:00
6807abff96
Made the code safer (at the expense of the memory usage).
2018-08-24 13:20:20 -04:00
94ea7cefb0
Moving include files into a sensible subdirectory.
2018-08-20 17:51:38 -04:00
ef0d14c35c
Minor fixes + new scripts.
2018-08-20 17:40:50 -04:00
fb65be64bb
Major surgery.
2018-08-20 17:27:25 -04:00
726eb5a030
Moved the files into subdirectories.
2018-08-20 14:45:51 -04:00
Daniel Lemire
Heinz N. Gies
technateNG
saka1
Dong Xie
Geoff Langdale
Tyler Kennedy
Georgios Floros
myd7349
Thomas Navennec
greedengineer
Carmot
M. Zhou
Kai Wolf
Wojciech Muła