CI test: Add Vale ci job test

.github/workflows/ci.yaml

@@ -42,5 +42,4 @@ jobs:
     - name: "Check manual line breaks"
       run:
         wget https://raw.githubusercontent.com/CharLotteiu/pingcap-docs-checks/main/check-manual-line-breaks.py;
-        python3 check-manual-line-breaks.py $(git diff-tree --name-only --no-commit-id -r upstream/master..HEAD -- '*.md' ':(exclude).github/*')
-
+        python3 check-manual-line-breaks.py $(git diff-tree --name-only --no-commit-id -r upstream/master..HEAD -- '*.md' ':(exclude).github/*')

.vale.ini

@@ -0,0 +1,5 @@
+StylesPath = styles
+MinAlertLevel = suggestion
+
+[*.md]
+BasedOnStyles = Google

en/test-file.md

@@ -0,0 +1,24 @@
+---
+title: test file
+summary: Learn the API of TiDB monitoring services.
+---
+
+### Binlog replication processing unit/sync unit
+
+Binlog replication processing unit is the processing unit used in DM-worker to read upstream binlogs or local relay logs, and to migrate these logs to the downstream. Each subtask corresponds to a binlog replication processing unit. In the current documentation, the binlog replication processing unit is also referred to as the sync processing unit.
+
+### Load processing unit/load unit
+
+The load processing unit is the processing unit used in DM-worker to import the fully exported data to the downstream. Each subtask corresponds to a load processing unit. In the current documentation, the load processing unit is also referred to as the import processing unit.
+
+### Subtask
+
+The subtask is a part of a data migration task that is running on each DM-worker instance. In different task configurations, a single data migration task might have one subtask or multiple subtasks.
+
+### Subtask status
+
+The subtask status is the status of a data migration subtask. The current status options include `New`, `Running`, `Paused`, `Stopped`, and `Finished`. Refer to [subtask status](query-status.md#subtask-status) for more details about the status of a data migration task or subtask.
+
+### `rows`
+
+Setting the `rows` option enables concurrently exporting data from a single table using multi-thread. The value of `rows` is the maximum number of rows contained in each exported chunk. After this option is enabled, DM selects a column as the split benchmark when the data of a MySQL single table is concurrently exported. This column can be one of the following columns: the primary key column, the unique index column, and the normal index column (ordered from highest priority to lowest). Make sure this column is of integer type (for example, `INT`, `MEDIUMINT`, `BIGINT`).

scripts/get-styles.py

@@ -0,0 +1,14 @@
+get_style () {
+    echo "Installing $2 from $1 ..."
+    curl -s https://api.github.com/repos/$1/$2/releases/latest \
+    | grep "browser_download_url.*zip" \
+    | cut -d : -f 2,3 \
+    | tr -d \" \
+    | wget -qi -
+}
+
+styles=( Google )
+for i in "${styles[@]}"
+do
+    get_style "errata-ai" $i
+done

styles/Google/AMPM.yml

@@ -0,0 +1,9 @@
+extends: existence
+message: "Use 'AM' or 'PM' (preceded by a space)."
+link: 'https://developers.google.com/style/word-list'
+level: error
+nonword: true
+tokens:
+  - '\d{1,2}[AP]M'
+  - '\d{1,2} ?[ap]m'
+  - '\d{1,2} ?[aApP]\.[mM]\.'

styles/Google/Acronyms.yml

@@ -0,0 +1,64 @@
+extends: conditional
+message: "Spell out '%s', if it's unfamiliar to the audience."
+link: 'https://developers.google.com/style/abbreviations'
+level: suggestion
+ignorecase: false
+# Ensures that the existence of 'first' implies the existence of 'second'.
+first: '\b([A-Z]{3,5})\b'
+second: '(?:\b[A-Z][a-z]+ )+\(([A-Z]{3,5})\)'
+# ... with the exception of these:
+exceptions:
+  - API
+  - ASP
+  - CLI
+  - CPU
+  - CSS
+  - CSV
+  - DEBUG
+  - DOM
+  - DPI
+  - FAQ
+  - GCC
+  - GDB
+  - GET
+  - GPU
+  - GTK
+  - GUI
+  - HTML
+  - HTTP
+  - HTTPS
+  - IDE
+  - JAR
+  - JSON
+  - JSX
+  - LESS
+  - LLDB
+  - NET
+  - NOTE
+  - NVDA
+  - OSS
+  - PATH
+  - PDF
+  - PHP
+  - POST
+  - RAM
+  - REPL
+  - RSA
+  - SCM
+  - SCSS
+  - SDK
+  - SQL
+  - SSH
+  - SSL
+  - SVG
+  - TBD
+  - TCP
+  - TODO
+  - URI
+  - URL
+  - USB
+  - UTF
+  - XML
+  - XSS
+  - YAML
+  - ZIP

styles/Google/Colons.yml

@@ -0,0 +1,7 @@
+extends: existence
+message: "'%s' should be in lowercase."
+link: 'https://developers.google.com/style/colons'
+nonword: true
+level: warning
+tokens:
+  - ':\s[A-Z]'

styles/Google/Contractions.yml

@@ -0,0 +1,30 @@
+extends: substitution
+message: "Feel free to use '%s' instead of '%s'."
+link: 'https://developers.google.com/style/contractions'
+level: suggestion
+ignorecase: true
+action:
+  name: replace
+swap:
+  are not: aren't
+  cannot: can't
+  could not: couldn't
+  did not: didn't
+  do not: don't
+  does not: doesn't
+  has not: hasn't
+  have not: haven't
+  how is: how's
+  is not: isn't
+  it is: it's
+  should not: shouldn't
+  that is: that's
+  they are: they're
+  was not: wasn't
+  we are: we're
+  we have: we've
+  were not: weren't
+  what is: what's
+  when is: when's
+  where is: where's
+  will not: won't

styles/Google/DateFormat.yml

@@ -0,0 +1,9 @@
+extends: existence
+message: "Use 'July 31, 2016' format, not '%s'."
+link: 'https://developers.google.com/style/dates-times'
+ignorecase: true
+level: error
+nonword: true
+tokens:
+  - '\d{1,2}(?:\.|/)\d{1,2}(?:\.|/)\d{4}'
+  - '\d{1,2} (?:Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)|May|Jun(?:e)|Jul(?:y)|Aug(?:ust)|Sep(?:tember)?|Oct(?:ober)|Nov(?:ember)?|Dec(?:ember)?) \d{4}'

styles/Google/Ellipses.yml

@@ -0,0 +1,9 @@
+extends: existence
+message: "In general, don't use an ellipsis."
+link: 'https://developers.google.com/style/ellipses'
+nonword: true
+level: warning
+action:
+  name: remove
+tokens:
+  - '\.\.\.'

styles/Google/EmDash.yml

@@ -0,0 +1,12 @@
+extends: existence
+message: "Don't put a space before or after a dash."
+link: 'https://developers.google.com/style/dashes'
+nonword: true
+level: error
+action:
+  name: edit
+  params:
+    - remove
+    - ' '
+tokens:
+  - '\s[—–]\s'

styles/Google/EnDash.yml

@@ -0,0 +1,13 @@
+extends: existence
+message: "Use an em dash ('—') instead of '–'."
+link: 'https://developers.google.com/style/dashes'
+nonword: true
+level: error
+action:
+  name: edit
+  params:
+    - replace
+    - '-'
+    - '—'
+tokens:
+  - '–'

styles/Google/Exclamation.yml

@@ -0,0 +1,7 @@
+extends: existence
+message: "Don't use exclamation points in text."
+link: 'https://developers.google.com/style/exclamation-points'
+nonword: true
+level: error
+tokens:
+  - '\w!(?:\s|$)'

styles/Google/FirstPerson.yml

@@ -0,0 +1,13 @@
+extends: existence
+message: "Avoid first-person pronouns such as '%s'."
+link: 'https://developers.google.com/style/pronouns#personal-pronouns'
+ignorecase: true
+level: warning
+nonword: true
+tokens:
+  - (?:^|\s)I\s
+  - (?:^|\s)I,\s
+  - \bI'm\b
+  - \bme\b
+  - \bmy\b
+  - \bmine\b

styles/Google/Gender.yml

@@ -0,0 +1,9 @@
+extends: existence
+message: "Don't use '%s' as a gender-neutral pronoun."
+link: 'https://developers.google.com/style/pronouns#gender-neutral-pronouns'
+level: error
+ignorecase: true
+tokens:
+  - he/she
+  - s/he
+  - \(s\)he

styles/Google/GenderBias.yml

@@ -0,0 +1,45 @@
+extends: substitution
+message: "Consider using '%s' instead of '%s'."
+link: 'https://developers.google.com/style/inclusive-documentation'
+ignorecase: true
+level: error
+swap:
+  (?:alumna|alumnus):          graduate
+  (?:alumnae|alumni):          graduates
+  air(?:m[ae]n|wom[ae]n):      pilot(s)
+  anchor(?:m[ae]n|wom[ae]n):   anchor(s)
+  authoress:                   author
+  camera(?:m[ae]n|wom[ae]n):   camera operator(s)
+  chair(?:m[ae]n|wom[ae]n):    chair(s)
+  congress(?:m[ae]n|wom[ae]n): member(s) of congress
+  door(?:m[ae]|wom[ae]n):      concierge(s)
+  draft(?:m[ae]n|wom[ae]n):    drafter(s)
+  fire(?:m[ae]n|wom[ae]n):     firefighter(s)
+  fisher(?:m[ae]n|wom[ae]n):   fisher(s)
+  fresh(?:m[ae]n|wom[ae]n):    first-year student(s)
+  garbage(?:m[ae]n|wom[ae]n):  waste collector(s)
+  lady lawyer:                 lawyer
+  ladylike:                    courteous
+  landlord:                    building manager
+  mail(?:m[ae]n|wom[ae]n):     mail carriers
+  man and wife:                husband and wife
+  man enough:                  strong enough
+  mankind:                     human kind
+  manmade:                     manufactured
+  manpower:                    personnel
+  men and girls:               men and women
+  middle(?:m[ae]n|wom[ae]n):   intermediary
+  news(?:m[ae]n|wom[ae]n):     journalist(s)
+  ombuds(?:man|woman):         ombuds
+  oneupmanship:                upstaging
+  poetess:                     poet
+  police(?:m[ae]n|wom[ae]n):   police officer(s)
+  repair(?:m[ae]n|wom[ae]n):   technician(s)
+  sales(?:m[ae]n|wom[ae]n):    salesperson or sales people
+  service(?:m[ae]n|wom[ae]n):  soldier(s)
+  steward(?:ess)?:             flight attendant
+  tribes(?:m[ae]n|wom[ae]n):   tribe member(s)
+  waitress:                    waiter
+  woman doctor:                doctor
+  woman scientist[s]?:         scientist(s)
+  work(?:m[ae]n|wom[ae]n):     worker(s)

styles/Google/HeadingPunctuation.yml

@@ -0,0 +1,13 @@
+extends: existence
+message: "Don't put a period at the end of a heading."
+link: 'https://developers.google.com/style/capitalization#capitalization-in-titles-and-headings'
+nonword: true
+level: warning
+scope: heading
+action:
+  name: edit
+  params:
+    - remove
+    - '.'
+tokens:
+  - '[a-z0-9][.](?:\s|$)'

styles/Google/Headings.yml

@@ -0,0 +1,26 @@
+extends: capitalization
+message: "'%s' should use sentence-style capitalization."
+link: 'https://developers.google.com/style/capitalization#capitalization-in-titles-and-headings'
+level: warning
+scope: heading
+match: $sentence
+exceptions:
+  - Azure
+  - CLI
+  - Code
+  - Cosmos
+  - Docker
+  - Emmet
+  - I
+  - Kubernetes
+  - Linux
+  - macOS
+  - Marketplace
+  - MongoDB
+  - REPL
+  - Studio
+  - TypeScript
+  - URLs
+  - Visual
+  - VS
+  - Windows

styles/Google/Latin.yml

@@ -0,0 +1,11 @@
+extends: substitution
+message: "Use '%s' instead of '%s'."
+link: 'https://developers.google.com/style/abbreviations'
+ignorecase: true
+level: error
+nonword: true
+action:
+  name: replace
+swap:
+  '\b(?:eg|e\.g\.)[\s,]': for example
+  '\b(?:ie|i\.e\.)[\s,]': that is

styles/Google/LyHyphens.yml

@@ -0,0 +1,14 @@
+extends: existence
+message: "'%s' doesn't need a hyphen."
+link: 'https://developers.google.com/style/hyphens'
+level: error
+ignorecase: false
+nonword: true
+action:
+  name: edit
+  params:
+    - replace
+    - '-'
+    - ' '
+tokens:
+  - '\s[^\s-]+ly-'

styles/Google/OptionalPlurals.yml

@@ -0,0 +1,12 @@
+extends: existence
+message: "Don't use plurals in parentheses such as in '%s'."
+link: 'https://developers.google.com/style/plurals-parentheses'
+level: error
+nonword: true
+action:
+  name: edit
+  params:
+    - remove
+    - '(s)'
+tokens:
+  - '\b\w+\(s\)'

styles/Google/Ordinal.yml

@@ -0,0 +1,7 @@
+extends: existence
+message: "Spell out all ordinal numbers ('%s') in text."
+link: 'https://developers.google.com/style/numbers'
+level: error
+nonword: true
+tokens:
+  - \d+(?:st|nd|rd|th)

styles/Google/OxfordComma.yml

@@ -0,0 +1,7 @@
+extends: existence
+message: "Use the Oxford comma in '%s'."
+link: 'https://developers.google.com/style/commas'
+scope: sentence
+level: warning
+tokens:
+  - '(?:[^,]+,){1,}\s\w+\s(?:and|or)'

styles/Google/Parens.yml

@@ -0,0 +1,7 @@
+extends: existence
+message: "Use parentheses judiciously."
+link: 'https://developers.google.com/style/parentheses'
+nonword: true
+level: suggestion
+tokens:
+  - '\(.+\)'