aboutsummaryrefslogtreecommitdiffstats
path: root/tests/data/release/63ht2plao5c4dasjeqj7vwglmq
diff options
context:
space:
mode:
Diffstat (limited to 'tests/data/release/63ht2plao5c4dasjeqj7vwglmq')
-rw-r--r--tests/data/release/63ht2plao5c4dasjeqj7vwglmq46
1 files changed, 46 insertions, 0 deletions
diff --git a/tests/data/release/63ht2plao5c4dasjeqj7vwglmq b/tests/data/release/63ht2plao5c4dasjeqj7vwglmq
new file mode 100644
index 0000000..41888ac
--- /dev/null
+++ b/tests/data/release/63ht2plao5c4dasjeqj7vwglmq
@@ -0,0 +1,46 @@
+{
+ "abstracts": [
+ {
+ "content": "The majority of text is stored in UTF-8, which must be validated on\ningestion. We present the lookup algorithm, which outperforms UTF-8 validation\nroutines used in many libraries and languages by more than 10 times using\ncommonly available SIMD instructions. To ensure reproducibility, our work is\nfreely available as open source software.",
+ "lang": "en",
+ "mimetype": "text/plain",
+ "sha1": "bb3b47ddb92b73cd378bd18ebee600472e817274"
+ }
+ ],
+ "contribs": [
+ {
+ "index": 0,
+ "raw_name": "John Keiser",
+ "role": "author"
+ },
+ {
+ "index": 1,
+ "raw_name": "Daniel Lemire",
+ "role": "author"
+ }
+ ],
+ "ext_ids": {
+ "arxiv": "2010.03090v1"
+ },
+ "extra": {
+ "arxiv": {
+ "base_id": "2010.03090",
+ "categories": [
+ "cs.DB"
+ ]
+ }
+ },
+ "ident": "63ht2plao5c4dasjeqj7vwglmq",
+ "language": "en",
+ "license_slug": "CC-BY",
+ "refs": [],
+ "release_date": "2020-10-06",
+ "release_stage": "submitted",
+ "release_type": "article",
+ "release_year": 2020,
+ "revision": "a66120cf-3c39-48da-8d90-f63513840bab",
+ "state": "active",
+ "title": "Validating UTF-8 In Less Than One Instruction Per Byte",
+ "version": "v1",
+ "work_id": "pgixwot2knfmtfq5pwjr4cazf4"
+}