From 97014a87c0dba41a4259661db53695082ed20eab Mon Sep 17 00:00:00 2001
From: Youwen Wu <youwenw@gmail.com>
Date: Thu, 4 Apr 2024 16:43:51 -0700
Subject: [PATCH] ci: add extra dictionary and patterns to spellcheck

---
 .github/actions/spelling/patterns.txt | 75 +++++++++++++++++++++++++++
 .github/workflows/spelling.yml        |  7 +++
 2 files changed, 82 insertions(+)
 create mode 100644 .github/actions/spelling/patterns.txt

diff --git a/.github/actions/spelling/patterns.txt b/.github/actions/spelling/patterns.txt
new file mode 100644
index 0000000..a5d58b5
--- /dev/null
+++ b/.github/actions/spelling/patterns.txt
@@ -0,0 +1,75 @@
+# Automatically suggested patterns
+# hit-count: 460 file-count: 2
+# base64 encoded content, possibly wrapped in mime
+(?:^|[\s=;:?])[-a-zA-Z=;:/0-9+]{50,}(?:[\s=;:?]|$)
+
+# hit-count: 129 file-count: 2
+# node packages
+(["'])@[^/'" ]+/[^/'" ]+\g{-1}
+
+# hit-count: 51 file-count: 2
+# version suffix <word>v#
+(?:(?<=[A-Z]{2})V|(?<=[a-z]{2}|[A-Z]{2})v)\d+(?:\b|(?=[a-zA-Z_]))
+
+# hit-count: 20 file-count: 2
+# IPv6
+\b(?:[0-9a-fA-F]{0,4}:){3,7}[0-9a-fA-F]{0,4}\b
+
+# hit-count: 17 file-count: 7
+# https/http/file urls
+(?:\b(?:https?|ftp|file)://)[-A-Za-z0-9+&@#/%?=~_|!:,.;]+[-A-Za-z0-9+&@#/%=~_|]
+
+# hit-count: 5 file-count: 1
+# latex (check-spelling >= 0.0.22)
+\\\w{2,}\{
+
+# hit-count: 4 file-count: 1
+# Lorem
+# Update Lorem based on your content (requires `ge` and `w` from https://github.com/jsoref/spelling; and `review` from https://github.com/check-spelling/check-spelling/wiki/Looking-for-items-locally )
+# grep '^[^#].*lorem' .github/actions/spelling/patterns.txt|perl -pne 's/.*i..\?://;s/\).*//' |tr '|' "\n"|sort -f |xargs -n1 ge|perl -pne 's/^[^:]*://'|sort -u|w|sed -e 's/ .*//'|w|review -
+# Warning, while `(?i)` is very neat and fancy, if you have some binary files that aren't proper unicode, you might run into:
+# ... Operation "substitution (s///)" returns its argument for non-Unicode code point 0x1C19AE (the code point will vary).
+# ... You could manually change `(?i)X...` to use `[Xx]...`
+# ... or you could add the files to your `excludes` file (a version after 0.0.19 should identify the file path)
+(?:(?:\w|\s|[,.])*\b(?i)(?:amet|consectetur|cursus|dolor|eros|ipsum|lacus|libero|ligula|lorem|magna|neque|nulla|suscipit|tempus)\b(?:\w|\s|[,.])*)
+
+# hit-count: 2 file-count: 2
+# w3
+\bw3\.org/[-0-9a-zA-Z/#.]+
+
+# hit-count: 2 file-count: 1
+# mailto urls
+mailto:[-a-zA-Z=;:/?%&0-9+@._]{3,}
+
+# hit-count: 2 file-count: 1
+# IServiceProvider / isAThing
+\b(?:I|isA)(?=(?:[A-Z][a-z]{2,})+(?:[A-Z]|\b))
+
+# hit-count: 2 file-count: 1
+# This does not cover multiline strings, if your repository has them,
+# you'll want to remove the `(?=.*?")` suffix.
+# The `(?=.*?")` suffix should limit the false positives rate
+# printf
+%(?:(?:(?:hh?|ll?|[jzt])?[diuoxn]|l?[cs]|L?[fega]|p)(?=[a-z]{2,})|(?:X|L?[FEGA]|p)(?=[a-zA-Z]{2,}))(?!%)(?=[_a-zA-Z]+(?!%)\b)(?=.*?['"])
+
+# hit-count: 2 file-count: 1
+# Alternative printf
+# %s
+%(?:s(?=[a-z]{2,}))(?!%)(?=[_a-zA-Z]+(?!%)\b)(?=.*?['"])
+
+# hit-count: 2 file-count: 1
+# libraries
+\blib(?!rar(?:ies|y))(?=[a-z])
+
+# hit-count: 1 file-count: 1
+# Twitter status
+\btwitter\.com/[^/\s"')]*(?:/status/\d+(?:\?[-_0-9a-zA-Z&=]*|)|)
+
+# hit-count: 1 file-count: 1
+# in check-spelling@v0.0.22+, printf markers aren't automatically consumed
+# printf markers
+(?<!\\)\\[nrt](?=[a-z]{2,})
+
+# hit-count: 1 file-count: 1
+# alternate printf markers if you run into latex and friends
+(?<!\\)\\[nrt](?=[a-z]{2,})(?=.*['"`])
diff --git a/.github/workflows/spelling.yml b/.github/workflows/spelling.yml
index f8513f3..dc94d82 100644
--- a/.github/workflows/spelling.yml
+++ b/.github/workflows/spelling.yml
@@ -106,6 +106,13 @@ jobs:
           use_sarif: ${{ (!github.event.pull_request || (github.event.pull_request.head.repo.full_name == github.repository)) && 1 }}
           extra_dictionary_limit: 20
           extra_dictionaries: cspell:software-terms/dict/softwareTerms.txt
+            cspell:css/css.txt
+            cspell:html/html.txt
+            cspell:svelte/src/svelte.txt
+            cspell:bash/src/bash-words.txt
+            cspell:lorem-ipsum/dictionary.txt
+            cspell:typescript/dict/typescript.txt
+            cspell:npm/dict/npm.txt
 
   comment-push:
     name: Report (Push)