simdjson
simdjson copied to clipboard
simdjson
Parsing gigabytes of JSON per second : used by Facebook/Meta Velox, the Node.js runtime, ClickHouse, WatermelonDB, Apache Doris, Milvus, StarRocks
I'm not sure how high of a priority the speed of writing out JSON is. But if it is, I have a prototype that runs in about 40% the time...
feature request: dom::array a; for(iter=a.rbegin();iter!=a.rend();iter++){ ... }
Currently, we parse `-0` as `0` (integer value) and `-0.0` as (-0, double value) in the DOM API.
Right now, we copy all strings to the string buffer because we don't know whether they contain escape characters--even though escape characters are few and far between (especially in keys)....
The simdjson library is highly optimized. Through clever optimizations, it avoids most bound checks. There are a few limitations. For example, we require a few bytes of padding at the...
| | v0.9.7 | current main branch | loss | |:--|:---|:------------|:------------ |partial_tweets | 3.13 GB/s | 2.95 GB/s | 6% | | large_random | 0.80 GB/s | 0.73 GB/s |...
ondemand::parser could use a load() method just like dom::parser has.
Presently, optional fields are difficult (but not impossible) to deal with. ```c++ auto json = R"( [ { "x": 1, "y": 2, "z": 3 } { "x": 1, "y": 2...
**Is your feature request related to a problem? Please describe.** The addition of On-Demand makes SimdJson fit very well our application domain. Besides Deserialization, we also would love to be...
For large files, the OnDemand API should have chunked indexing. As remarked by @jkeiser in https://github.com/simdjson/simdjson/pull/1351 one needs to take into account that when visiting the keys of an object,...