diff options
| -rw-r--r-- | tests/data/release/5a22nt42bvfj7m3dzfm7br73ni | 46 | ||||
| -rw-r--r-- | tests/data/release/63ht2plao5c4dasjeqj7vwglmq | 46 | ||||
| -rw-r--r-- | tests/data/release/zchlsocreffbdm36qhzy3cs32e | 287 | ||||
| -rw-r--r-- | tests/data/verify.csv | 5 |
4 files changed, 383 insertions, 1 deletions
diff --git a/tests/data/release/5a22nt42bvfj7m3dzfm7br73ni b/tests/data/release/5a22nt42bvfj7m3dzfm7br73ni new file mode 100644 index 0000000..dbd6354 --- /dev/null +++ b/tests/data/release/5a22nt42bvfj7m3dzfm7br73ni @@ -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": "2010.03090v2" + }, + "extra": { + "arxiv": { + "base_id": "2010.03090", + "categories": [ + "cs.DB" + ] + } + }, + "ident": "5a22nt42bvfj7m3dzfm7br73ni", + "language": "en", + "license_slug": "CC-BY", + "refs": [], + "release_date": "2020-10-10", + "release_stage": "submitted", + "release_type": "article", + "release_year": 2020, + "revision": "305afdf5-ae10-49bf-a740-ea1740390afb", + "state": "active", + "title": "Validating UTF-8 In Less Than One Instruction Per Byte", + "version": "v2", + "work_id": "pgixwot2knfmtfq5pwjr4cazf4" +} 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" +} diff --git a/tests/data/release/zchlsocreffbdm36qhzy3cs32e b/tests/data/release/zchlsocreffbdm36qhzy3cs32e new file mode 100644 index 0000000..9007c19 --- /dev/null +++ b/tests/data/release/zchlsocreffbdm36qhzy3cs32e @@ -0,0 +1,287 @@ +{ + "abstracts": [], + "container_id": "afve5b3tavbfzch46mdtazbqla", + "contribs": [ + { + "extra": { + "seq": "first" + }, + "given_name": "John", + "index": 0, + "raw_affiliation": "Microsoft Redmond Washington USA", + "raw_name": "John Keiser", + "role": "author", + "surname": "Keiser" + }, + { + "creator_id": "d7rv3jglprcd5nloqpfonppiom", + "given_name": "Daniel", + "index": 1, + "raw_affiliation": "DOT‐Lab Research Center Université du Québec (TELUQ) Montreal Quebec Canada", + "raw_name": "Daniel Lemire", + "role": "author", + "surname": "Lemire" + } + ], + "ext_ids": { + "doi": "10.1002/spe.2920" + }, + "extra": { + "crossref": { + "alternative-id": [ + "10.1002/spe.2920" + ], + "archive": [ + "Portico" + ], + "funder": [ + { + "DOI": "10.13039/501100000046", + "award": [ + "RGPIN‐2017‐03910" + ], + "doi-asserted-by": "publisher", + "name": "National Research Council Canada" + } + ], + "license": [ + { + "URL": "http://onlinelibrary.wiley.com/termsAndConditions#vor", + "content-version": "vor", + "delay-in-days": 0, + "start": "2020-10-29T00:00:00Z" + } + ], + "subject": [ + "Software" + ], + "type": "journal-article" + } + }, + "ident": "zchlsocreffbdm36qhzy3cs32e", + "language": "en", + "publisher": "Wiley", + "refs": [ + { + "extra": { + "unstructured": "YergeauF UTF‐8 a transformation format of ISO 10646; internet engineering task force request for comments 3629;2015.https://tools.ietf.org/html/rfc3629. Accessed July 2020." + }, + "index": 0, + "key": "e_1_2_11_2_1" + }, + { + "extra": { + "unstructured": "The MITRE CorporationCAPEC‐80: using UTF‐8 encoding to bypass validation logic;2019.https://capec.mitre.org/data/definitions/80.html. Accessed July 2020." + }, + "index": 1, + "key": "e_1_2_11_3_1" + }, + { + "extra": { + "unstructured": "ColletY. LZ4 ‐ Extremely fast compression;2020.https://github.com/lz4/lz4. Accessed July 2020." + }, + "index": 2, + "key": "e_1_2_11_4_1" + }, + { + "container_name": "IEEE Softw", + "extra": { + "authors": [ + "Suneja N" + ], + "doi": "10.1109/ms.2019.2909854", + "volume": "36" + }, + "index": 3, + "key": "e_1_2_11_5_1", + "locator": "96", + "title": "Scylladb optimizes database architecture to maximize hardware performance", + "year": 2019 + }, + { + "extra": { + "unstructured": "CaiY. Utils: optimize UTF‐8 validation;2019.https://bit.ly/2VrlQ37. Accessed July 2020." + }, + "index": 4, + "key": "e_1_2_11_6_1" + }, + { + "container_name": "2012 SC Companion: High Performance Computing, Networking Storage and Analysis", + "extra": { + "authors": [ + "Cebrián JM" + ], + "doi": "10.1109/sc.companion.2012.93", + "volume-title": "2012 SC Companion: High Performance Computing, Networking Storage and Analysis" + }, + "index": 5, + "key": "e_1_2_11_7_1", + "locator": "675", + "year": 2012 + }, + { + "extra": { + "doi": "10.1145/1133255.1133997" + }, + "index": 6, + "key": "e_1_2_11_8_1" + }, + { + "extra": { + "doi": "10.1109/iceccs.2013.40", + "unstructured": "XiaX LoD ZhuF WangX ZhouB. Software internationalization and localization: an industrial experience. Paper presented at: Proceedings of the 2013 18th International Conference on Engineering of Complex Computer Systems Singapore;2013:222‐231." + }, + "index": 7, + "key": "e_1_2_11_9_1" + }, + { + "container_name": "IITM J Manag IT", + "extra": { + "authors": [ + "Singh T" + ], + "volume": "10" + }, + "index": 8, + "key": "e_1_2_11_10_1", + "locator": "65", + "title": "Fuchsia OS‐a threat to android", + "year": 2019 + }, + { + "extra": { + "unstructured": "HöhrmannB Flexible and economical UTF‐8 decoder;2010.http://bjoern.hoehrmann.de/utf‐8/decoder/dfa/. Accessed July 2020." + }, + "index": 9, + "key": "e_1_2_11_11_1" + }, + { + "container_name": "VLDB J", + "extra": { + "authors": [ + "Langdale G" + ], + "doi": "10.1007/s00778-019-00578-5", + "volume": "28" + }, + "index": 10, + "key": "e_1_2_11_12_1", + "locator": "941", + "title": "Parsing gigabytes of JSON per second", + "year": 2019 + }, + { + "extra": { + "doi": "10.1007/978-1-4684-2001-2_9" + }, + "index": 11, + "key": "e_1_2_11_13_1" + }, + { + "extra": { + "doi": "10.1145/2807591.2807644", + "unstructured": "HoeflerT BelliR. Scientific benchmarking of parallel computing systems: twelve ways to tell the masses when reporting performance results. Paper presented at: Proceedings of the International Conference for High Performance Computing Networking Storage and Analysis Austin Texas;2015:1‐12." + }, + "index": 12, + "key": "e_1_2_11_14_1" + }, + { + "container_name": "ACM Trans Web", + "extra": { + "authors": [ + "Muła W" + ], + "doi": "10.1145/3132709", + "volume": "12" + }, + "index": 13, + "key": "e_1_2_11_15_1", + "title": "Faster Base64 encoding and decoding using AVX2 instructions", + "year": 2018 + }, + { + "extra": { + "doi": "10.1002/spe.2777" + }, + "index": 14, + "key": "e_1_2_11_16_1" + }, + { + "extra": { + "doi": "10.1145/1463788.1463811", + "unstructured": "CameronRD HerdyKS LinD. High performance XML parsing using parallel bit stream technology. Paper presented at: Proceedings of the 2008 Conference of the Center for Advanced Studies on Collaborative Research: Meeting of Minds CASCON '08;2008:17:222–17:235; New York NY ACM." + }, + "index": 15, + "key": "e_1_2_11_17_1" + }, + { + "extra": { + "doi": "10.1145/2541940.2541988", + "unstructured": "MytkowiczT MusuvathiM SchulteW. Data‐parallel finite‐state machines. Paper presented at: Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems ASPLOS '14;2014:529‐542; New York NY ACM." + }, + "index": 16, + "key": "e_1_2_11_18_1" + }, + { + "container_name": "Proc VLDB Endow", + "extra": { + "authors": [ + "Mühlbauer T" + ], + "doi": "10.14778/2556549.2556555", + "issue": "14" + }, + "index": 17, + "key": "e_1_2_11_19_1", + "locator": "1702", + "title": "Instant loading for main memory databases", + "year": 2013 + }, + { + "extra": { + "doi": "10.1145/1345206.1345222", + "unstructured": "CameronRD. A case study in SIMD text processing with parallel bit streams: UTF‐8 to UTF‐16 transcoding. Paper presented at: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming;2008:91‐98; ACM New York NY." + }, + "index": 18, + "key": "e_1_2_11_20_1" + }, + { + "extra": { + "doi": "10.1145/3018743.3018760", + "unstructured": "JiangP AgrawalG.Combining SIMD and Many/Multi‐core parallelism for finite state machines with enumerative speculation. Paper presented at: Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming Austin Texas;2017:179‐191." + }, + "index": 19, + "key": "e_1_2_11_21_1" + }, + { + "extra": { + "doi": "10.1109/mm.2017.35" + }, + "index": 20, + "key": "e_1_2_11_22_1" + }, + { + "container_name": "Perform Eval", + "extra": { + "authors": [ + "Pohl A" + ], + "doi": "10.1016/j.peva.2020.102106", + "volume": "140" + }, + "index": 21, + "key": "e_1_2_11_23_1", + "locator": "102106", + "title": "Vectorization cost modeling for NEON, AVX and SVE", + "year": 2020 + } + ], + "release_date": "2020-10-29", + "release_stage": "published", + "release_type": "article-journal", + "release_year": 2020, + "revision": "4da1f7f7-f39e-4487-aca2-8626b9009497", + "state": "active", + "title": "Validating UTF‐8 in less than one instruction per byte", + "work_id": "izbh6u37vzb2fauftewcwdxi4m" +} diff --git a/tests/data/verify.csv b/tests/data/verify.csv index c4d5172..af05113 100644 --- a/tests/data/verify.csv +++ b/tests/data/verify.csv @@ -117,4 +117,7 @@ vqjpcuqxnbhdtelzspxjmklm7u,knuzh5bcqbg7ph7ffvqaiwevti,Status.AMBIGUOUS,Miss.CUST psykbwxylndtdaand2ymtkgzqu,xizkwvsodzajnn4u7lgeldqoum,Status.DIFFERENT,Miss.YEAR nb4yakyqebalbatnnfijkfhmka,pr7e4l5eibaavm3zsk62nmphni,Status.STRONG,OK.SLUG_TITLE_AUTHOR_MATCH in2mm2wafbczjgzlapq55rrksq,oaezupjwnfckxaajjhjb3fl42e,Status.AMBIGUOUS, -u4mjilmo75bcnjyms564l66jea,6ofr4mqnmrdy3nyyh5ufm5ats4,Status.EXACT, +u4mjilmo75bcnjyms564l66jea,6ofr4mqnmrdy3nyyh5ufm5ats4,Status.AMBIGUOUS, +5a22nt42bvfj7m3dzfm7br73ni,63ht2plao5c4dasjeqj7vwglmq,Status.EXACT,OK.WORK_ID +5a22nt42bvfj7m3dzfm7br73ni,zchlsocreffbdm36qhzy3cs32e,Status.STRONG, +63ht2plao5c4dasjeqj7vwglmq,zchlsocreffbdm36qhzy3cs32e,Status.STRONG, |