chore: import upstream snapshot with attribution

This commit is contained in:
wehub-resource-sync
2026-07-13 13:30:30 +08:00
commit 914fea506e
2793 changed files with 802106 additions and 0 deletions
@@ -0,0 +1,323 @@
# reject `m_data` as VxWorks defined it and that breaks things if it's used elsewhere
# see [fprime](https://github.com/nasa/fprime/commit/d589f0a25c59ea9a800d851ea84c2f5df02fb529)
# and [Qt](https://github.com/qtproject/qt-solutions/blame/fb7bc42bfcc578ff3fa3b9ca21a41e96eb37c1c7/qtscriptclassic/src/qscriptbuffer_p.h#L46)
#\bm_data\b
# Were you debugging using a framework with `fit()`?
# If you have a framework that uses `it()` for testing and `fit()` for debugging a specific test,
# you might not want to check in code where you skip all the other tests.
#\bfit\(
# Should be `HH:MM:SS`
\bHH:SS:MM\b
# Should be `86400` (seconds in a standard day)
\b84600\b(?:.*\bday\b)
# Should probably be `2006-01-02` (yyyy-mm-dd)
\b2006-01-02\b
# Should probably be `YYYYMMDD`
\b[Yy]{4}[Dd]{2}[Mm]{2}(?!.*[Yy]{4}[Dd]{2}[Mm]{2}).*$
# Should be `anymore`
\bany more[,.]
# Should be `cannot` (or `can't`)
# See https://www.grammarly.com/blog/cannot-or-can-not/
# > Don't use `can not` when you mean `cannot`. The only time you're likely to see `can not` written as separate words is when the word `can` happens to precede some other phrase that happens to start with `not`.
# > `Can't` is a contraction of `cannot`, and it's best suited for informal writing.
# > In formal writing and where contractions are frowned upon, use `cannot`.
# > It is possible to write `can not`, but you generally find it only as part of some other construction, such as `not only . . . but also.`
# - if you encounter such a case, add a pattern for that case to patterns.txt.
\b[Cc]an not\b
# Should be `GitHub`
(?<![&*.]|// |\btype |\bimport )\bGithub\b(?![{()])
\b[Gg]it\s[Hh]ub\b
# Should be `GitLab`
(?<![&*.]|// |\btype )\bGitlab\b(?![{)])
# Should be `JavaScript`
\bJavascript\b
# Should be `macOS` or `Mac OS X` or ...
\bMacOS\b
# Should be `Microsoft`
\bMicroSoft\b
# Should be `OAuth`
(?:^|[^-/*$])[ '"]oAuth(?: [a-z]|\d+ |[^ a-zA-Z0-9:;_.()])
# Should be `RabbitMQ`
\bRabbitmq\b
# Should be `TypeScript`
\bTypescript\b
# Should be `another`
\ban[- ]other\b
# Should be `case-(in)sensitive`
\bcase (?:in|)sensitive\b
# Should be `coinciding`
\bco-inciding\b
# Should be `deprecation warning(s)`
\b[Dd]epreciation [Ww]arnings?\b
# Should be `greater than`
\bgreater then\b
# Should be `ID`
#\bId\b
# Should be `in front of`
\bin from of\b
# Should be `into`
# when not phrasal and when `in order to` would be wrong:
# https://thewritepractice.com/into-vs-in-to/
\sin to\s(?!if\b)
# Should be `use`
\sin used by\b
# Should be `is obsolete`
\bis obsolescent\b
# Should be `it's` or `its`
\bits[']
# Should be `its`
\bit's(?= own\b)
# Should be `perform its`
\bperform it's\b
# Should be `opt-in`
(?<!\sfor)\sopt in\s
# Should be `less than`
\bless then\b
# Should be `load balancer`
\b[Ll]oud balancer
# Should be `one of`
\bon of\b
# Should be `otherwise`
\bother[- ]wise\b
# Should be `or (more|less)`
\bore (?:more|less)\b
# Should be `rather than`
\brather then\b
# Should be `regardless, ...` or `regardless of (whether)`
\b[Rr]egardless if you\b
# Should be `no longer needed`
\bno more needed\b(?! than\b)
# Should be `did not exist`
\bwere not existent\b
# Should be `nonexistent`
\bnon existing\b
# Should be `nonexistent`
\b[Nn]o[nt][- ]existent\b
# Should be `@brief` / `@details` / `@param` / `@return` / `@retval`
(?:^\s*|(?:\*|//|/*)\s+`)[\\@](?:breif|(?:detail|detials)|(?:params(?!\.)|prama?)|ret(?:uns?)|retvl)\b
# Should be `preexisting`
[Pp]re[- ]existing
# Should be `preempt`
[Pp]re[- ]empt\b
# Should be `preemptively`
[Pp]re[- ]emptively
# Should be `recently changed` or `recent changes`
[Rr]ecent changed
# Should be `reentrancy`
[Rr]e[- ]entrancy
# Should be `reentrant`
[Rr]e[- ]entrant
# Should be `understand`
\bunder stand\b
# Should be `workarounds`
\bwork[- ]arounds\b
# Should be `workaround`
(?:(?:[Aa]|[Tt]he|ugly)\swork[- ]around\b|\swork[- ]around\s+for)
# Should be `(coarse|fine)-grained`
\b(?:coarse|fine) grained\b
# Should be `neither/nor` -- or reword
\bnot\b[^.?!"/(]+\bnor\b
# Should be `neither/nor` (plus rewording the beginning)
# This is probably a double negative...
\bnot\b[^.?!"/]*\bneither\b[^.?!"/(]*\bnor\b
# In English, duplicated words are generally mistakes
# There are a few exceptions (e.g. "that that").
# If the highlighted doubled word pair is in:
# * code, write a pattern to mask it.
# * prose, have someone read the English before you dismiss this error.
\s([A-Z]{3,}|[A-Z][a-z]{2,}|[a-z]{3,})\s\g{-1}\s
# Should be `Gen AI`
\b[gG]enAI\b
# Should be LangChain
\b(?!LangChain\b)(?!langchain\b)[Ll]ang\s?[Cc]hain?\b
# Should be LangGraph
\b(?!LangGraph\b)(?!langgraph\b)[Ll]ang\s?[Gg]raph?\b
# Should be LangServe
\b(?!LangServe\b)(?!langserve\b)[Ll]ang\s?[Ss]erve?\b
# Should be LlamaIndex
\b(?!LlamaIndex\b)[Ll][Ll]ama\s?[Ii]ndex?\s
# Should be Hugging Face
\s(?!Hugging Face\b)[Hh]ugging\s?[Ff]ace?\b
# Should be DeepSeek
\b(?!DeepSeek\b)(?!deepseek\b)[Dd]eep\s?[Ss]eek?\b
# Should be Agent Platform
^(?!.*Agent Platform).*\b[Vv]ertex[-\s][Aa][Ii]\b
# Should be Gemini
\sgemini\s\w
# Should be `Gemini Version Size` (e.g. `Gemini 3 Flash`)
\bGemini\s(Pro|Flash|Ultra)\s?\d\.\d\b
# Gemini Size should be capitalized (e.g. `Gemini 3 Flash`)
\bGemini\s?\d\.\d\s(pro|flash|ultra)\b
# Don't say "Google Gemini" or "Google Gemini"
\b[Gg]oogle(?: [Cc]loud| [Dd]eep[Mm]ind)?'s [Gg]emini\b
# Don't say "Powered by Gemini", instead say "with Gemini"
\b[Pp]owered\s[Bb]y\s[Gg]emini\b
# Should be Gemini Enterprise
[Aa]gent\s?[Ss]pace
# Should be Imagen
\simagen\s\w
# Should be Imagen 2 or Imagen 3
\bImagen\d\b
# Should be BigQuery
\b(?!BigQuery\b)(?!bigquery\b)[Bb]ig\s?[Qq]uery\b
# Should be DataFrame or DataFrames
\b(?!DataFrames?\b)(?!.*[\(\)\{\}\.,=])(?<!")\b[Dd]ata\s?[Ff]rames?\b(?!")
# Should be Google Cloud
\s[Gg][Cc][Pp]\s
# Should be Google Cloud
\b(?!Google\sCloud\b)[Gg]oogle\s?[Cc]loud\b
# Should be DeepMind
\b(?!DeepMind\b)[Dd]eep\s?[Mm]ind\b
# Should be TensorFlow
\b(?!TensorFlow\b)(?!tensorflow\b)[Tt]ensor\s?[Ff]low\b
# Should be AlloyDB
\b(?!AlloyDB\b)(?!alloydb\b)[Aa]lloy\s?[Dd]\s?[Bb]\b
# Should be Translation API
\bTranslate\s?API\b
# Should be Dialogflow
\bDialogFlow\b
# Should be Firebase
\b(?!Firebase\b)Fire\s?[Bb]ase\b
# Should be Firestore
\b(?!Firestore\b)Fire\s?[Ss]tore\b
# Should be Memorystore
\b(?!Memorystore\b)Memory\s?[Ss]tore\b
# Should be Document AI
\bDoc\s?AI\b
# Should be Agent Search
\bVertex\s?Search\b
# Should be Vector Search
\bVertex\sVector\sSearch\b
# Should be Colab
\s(?!Colab)Co[Ll][Ll]?abs?\b
# Should be TPU or TPUs
\btpus?\b
# Should be GCS
\sgcs\s
# Should be Dataflow ML
\b[Dd]ataflowML\b
# Should be API
\s(?!API)(?!.*[\(\)\{\},=#]+)[Aa][Pp][Ii]\s
# Should be arXiv
\bAr[Xx]iv\b
# Should be DeepEval
\b(?!DeepEval\b)(?!deepeval\b)[Dd]eep\s?[Ee]val\b
# Invalid Space Character
\w \w
# Don't use "smart quotes"
(?<!["'])[‘’“”](?!["'])
# "an" should only be before vowels.
\ban\s+(?![FHLMNRSX][A-Z0-9]+\b)(?!hour\b)(?!honest\b)([b-df-hj-np-tv-zB-DF-HJ-NP-TV-Z]{1}\w*)
# Don't use Google internal links
((corp|prod|sandbox).google.com|googleplex.com|https?://[0-9a-z][0-9a-z-]+/|(?:^|[^/.-])\b(?:go|b|cl|cr)/[a-z0-9_.-]+\b)
# Use `%pip` instead of `!pip` or `!pip3`
!\s?pip3?
# Don't use embedded images, upload to Google Cloud Storage
\(data:image/(?:jpeg|png);base64,[^{]
# Don't use Gemini 1.X
gemini-1\.[05]
# Use the Google Gen AI SDK `google-genai`
google-generativeai
from google import generativeai
cloud-llm-preview[1-4]