Title: Speed up JSON string decoding for documents with long string values · Issue #150871 · python/cpython · GitHub
Open Graph Title: Speed up JSON string decoding for documents with long string values · Issue #150871 · python/cpython
X Title: Speed up JSON string decoding for documents with long string values · Issue #150871 · python/cpython
Description: Proposal The C JSON decoder finds the end of every string by reading one character at a time, checking each for the closing quote, a backslash, or a control character (scanstring_unicode in Modules/_json.c). For a string with a long run ...
Open Graph Description: Proposal The C JSON decoder finds the end of every string by reading one character at a time, checking each for the closing quote, a backslash, or a control character (scanstring_unicode in Modules...
X Description: Proposal The C JSON decoder finds the end of every string by reading one character at a time, checking each for the closing quote, a backslash, or a control character (scanstring_unicode in Modules...
Opengraph URL: https://github.com/python/cpython/issues/150871
X: @github
Domain: github.com
{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"Speed up JSON string decoding for documents with long string values","articleBody":"### Proposal\n\nThe C JSON decoder finds the end of every string by reading one character at a time, checking each for the closing quote, a backslash, or a control character (`scanstring_unicode` in `Modules/_json.c`). For a string with a long run of ordinary characters, such as a log line, a text field, or a base64 or embedded-document value, that loop does one read and several comparisons per byte while the machine's 64-bit registers sit mostly idle.\n\nThe proposal is to scan the one-byte (ASCII/Latin-1) representation eight bytes at a time: load eight bytes into a single machine word and test all eight at once for the closing quote, a backslash, or a control character. A run of ordinary characters then advances eight bytes per step. At the first byte that needs attention, the existing per-character loop takes over, so every decode decision stays on the current path. Two-byte and four-byte strings (anything containing a non-Latin-1 character) keep the current loop unchanged.\n\nIn one line: today the decoder asks \"is this byte special?\" once per byte; this asks \"is any of these eight bytes special?\" once per eight, and drops to per-byte only when the answer is yes.\n\n### How this differs from the SIMD backend in #142915\n\nThis is not the SIMD parsing architecture declined in #142915. It uses no SIMD intrinsics, no runtime CPU detection, and no build configuration. It relies only on portable 64-bit integer arithmetic, with the same `0x0101…` / `0x8080…` masks that `Objects/unicodeobject.c` already applies for ASCII scanning. It changes one function and adds no infrastructure, so it does not depend on #125022 and needs no PEP.\n\nThe single-character `find_char` from `fastsearch.h` (adopted for the SRE prefix scanner in #148729) does not fit here: a JSON string scan stops at the first of three different bytes, and the strict-mode control-character test is a character-class check that a single-character search cannot express. A word-at-a-time mask handles the class in one operation.\n\n### When it helps, and when it does not\n\nMeasured `json.loads` speedups against the current decoder:\n\n| Document shape | Effect |\n|---|---|\n| One long text field (~11 KB string) | 6.3x faster |\n| Many 200-character ASCII string values | 4.5x faster |\n| Realistic mixed records (short and medium strings) | 1.17x faster |\n| Short keys, numbers, the pyperformance document | no change |\n| Strings with emoji or other non-Latin-1 text | no change (scalar path) |\n\nThe standard `pyperformance bm_json_loads` document is short-string and dict dominated, so it shows no change. The benefit is specific to documents whose payload is long text.\n\n### Correctness\n\nThe decoded output is byte-identical to the current decoder. A proof-of-concept patch is validated against `test_json`, a 347-input differential corpus (real-world JSON plus a special character placed at every offset across the eight-byte window, in all three string representations), and all 340 files of `nst/JSONTestSuite` (318 parsing plus 22 transform). Every value and every error position matches.\n\n### Relation to other json work\n\nIndependent of, and complementary to, the active number-parsing (#150639) and encoder (#150827) changes.\n\nA proof-of-concept PR follows.\n\n### Benchmark\n\nBuilt base and patched interpreters from this branch's `main` ancestor and the patch, ran the same script under each, and compared with `pyperf compare_to` (A/B by swapping `Lib/json/decoder.py` on the same build; macOS arm64, non-PGO).\n\n```python\nimport json, pyperf\n# Ceiling probe: vary string length & kind to expose where SWAR string-scan helps.\nlong_ascii = json.dumps([(\"x\"*200) for _ in range(200)]) # long ASCII values -> max win\ntext_blob = json.dumps({\"body\": \"lorem ipsum dolor sit amet \" * 400}) # one huge string\nshort_keys = json.dumps({f\"k{i}\": i for i in range(2000)}) # short keys -> minimal win\nmixed_real = json.dumps([{\"id\":i,\"name\":f\"user_{i}\",\"email\":f\"u{i}@example.com\",\"bio\":\"hello \"*10} for i in range(300)])\nmultikind = json.dumps([\"emoji 😀 中文 текст \"*20 for _ in range(200)]) # UCS-2/4 -> scalar fallback (neutral check)\n# pyperformance dataset\nSD={'key1':0,'key2':True,'key3':'value','key4':'foo','key5':'string'}\nND={'key1':0,'key2':SD,'key3':'value','key4':SD,'key5':SD,'key':'ąćż'}\nppset=[(json.dumps({}),2000),(json.dumps(SD),1000),(json.dumps(ND),1000),(json.dumps([ND]*1000),1)]\n\ndocs = {\"long_ascii_values\": long_ascii, \"huge_text_blob\": text_blob,\n \"short_keys\": short_keys, \"mixed_real\": mixed_real, \"multikind_emoji\": multikind}\nrunner = pyperf.Runner()\nfor name, s in docs.items():\n runner.bench_func(f\"loads/{name}\", lambda s=s: json.loads(s))\ndef pp(items):\n for s,n in items:\n for _ in range(n): json.loads(s)\nrunner.bench_func(\"loads/pyperformance\", pp, ppset)\n```\n\n\u003c!-- gh-linked-prs -->\n### Linked PRs\n* gh-150872\n\u003c!-- /gh-linked-prs -->\n\n\n","author":{"url":"https://github.com/gaborbernat","@type":"Person","name":"gaborbernat"},"datePublished":"2026-06-03T16:22:34Z","url":"https://github.com/python/cpython/issues/150871"}
| react-profiling | 0 |
| react-import-map | react,react-dom,react-dom/client,react-dom/profiling,react-is,react/compiler-runtime,react/jsx-dev-runtime,react/jsx-runtime,scheduler@b8488ee2c322 |
| route-pattern | /_view_fragments/issues/show/:user_id/:repository/:id/issue_layout(.:format) |
| route-controller | voltron_issues_fragments |
| route-action | issue_layout |
| fetch-nonce | v2:fba10110-cea9-605c-be13-f157c9e644d6 |
| current-catalog-service-hash | 81bb79d38c15960b92d99bca9288a9108c7a47b18f2423d0f6438c5b7bcd2114 |
| request-id | ECEE:2270F4:34B808F:45ED13C:6B01FA0A |
| html-safe-nonce | ffb0bc1a4763fdd7ed0c49b5bfdae26c1e70fb58551d6b3f5f29e46beb200bc8 |
| visitor-payload | eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJFQ0VFOjIyNzBGNDozNEI4MDhGOjQ1RUQxM0M6NkIwMUZBMEEiLCJ2aXNpdG9yX2lkIjoiODUzNDA3MzQ4NDYzOTMzNjk3MCIsInJlZ2lvbl9lZGdlIjoiaWFkIiwicmVnaW9uX3JlbmRlciI6ImlhZCJ9 |
| visitor-hmac | 8b379f1ea2b5fa688fed001ec01835a443217ce8f8e642968ced61e4cadd4b76 |
| hovercard-subject-tag | issue:4581698882 |
| github-keyboard-shortcuts | repository,issues,copilot |
| google-site-verification | Apib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I |
| octolytics-url | https://collector.github.com/github/collect |
| analytics-location | / |
| fb:app_id | 1401488693436528 |
| apple-itunes-app | app-id=1477376905, app-argument=https://github.com/_view_fragments/issues/show/python/cpython/150871/issue_layout |
| twitter:image | https://opengraph.githubassets.com/9d2f11d1eb9c9fea2d4b46563e436cf91d8eaeb4d4c723d0a79ebc65711c5873/python/cpython/issues/150871 |
| twitter:card | summary_large_image |
| og:image | https://opengraph.githubassets.com/9d2f11d1eb9c9fea2d4b46563e436cf91d8eaeb4d4c723d0a79ebc65711c5873/python/cpython/issues/150871 |
| og:image:alt | Proposal The C JSON decoder finds the end of every string by reading one character at a time, checking each for the closing quote, a backslash, or a control character (scanstring_unicode in Modules... |
| og:image:width | 1200 |
| og:image:height | 600 |
| og:site_name | GitHub |
| og:type | object |
| og:author:username | gaborbernat |
| hostname | github.com |
| expected-hostname | github.com |
| None | 87e774ee7c6b3bee0490394e4d3e57ec9dbc956f74b87ea685dc8996c1676456 |
| turbo-cache-control | no-preview |
| go-import | github.com/python/cpython git https://github.com/python/cpython.git |
| octolytics-dimension-user_id | 1525981 |
| octolytics-dimension-user_login | python |
| octolytics-dimension-repository_id | 81598961 |
| octolytics-dimension-repository_nwo | python/cpython |
| octolytics-dimension-repository_public | true |
| octolytics-dimension-repository_is_fork | false |
| octolytics-dimension-repository_network_root_id | 81598961 |
| octolytics-dimension-repository_network_root_nwo | python/cpython |
| turbo-body-classes | logged-out env-production page-responsive |
| disable-turbo | false |
| browser-stats-url | https://api.github.com/_private/browser/stats |
| browser-errors-url | https://api.github.com/_private/browser/errors |
| release | 423dbb54c5e7bfecc838eb387c1435eb3d0e760d |
| ui-target | full |
| theme-color | #1e2327 |
| color-scheme | light dark |
| react-app-name | issues |
Links:
Viewport: width=device-width