Add some Vale styles (#2963)

* add some styles

Signed-off-by: Jo Stichbury <jo_stichbury@mckinsey.com>

* Tweaks to styles

Signed-off-by: Jo Stichbury <jo_stichbury@mckinsey.com>

* more tweaks

Signed-off-by: Jo Stichbury <jo_stichbury@mckinsey.com>

* Revise some styles

Signed-off-by: Jo Stichbury <jo_stichbury@mckinsey.com>

* Revise severity of some styles

Signed-off-by: Jo Stichbury <jo_stichbury@mckinsey.com>

* Update .github/styles/Kedro/words.yml

Co-authored-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

---------

Signed-off-by: Jo Stichbury <jo_stichbury@mckinsey.com>
Co-authored-by: Deepyaman Datta <deepyaman.datta@utexas.edu>

.github/styles/Kedro/abbreviations.yml

@@ -0,0 +1,11 @@
+extends: substitution
+message: "Use '%s' instead of abbreviations like '%s'."
+ignorecase: true
+level: warning
+nonword: true
+action:
+  name: replace
+swap:
+  '\b(?:eg|e\.g\.|eg\.)[\s,]': for example
+  '\b(?:ie|i\.e\.|ie\.)[\s,]': that is
+  '\b(?:etc)[\s\n,.]': and more

.github/styles/Kedro/gender.yml

@@ -0,0 +1,13 @@
+extends: existence
+message: "Use a gender-neutral pronoun instead of '%s'."
+level: error
+ignorecase: true
+tokens:
+  - he/she
+  - s/he
+  - \(s\)he
+  - \bhe\b
+  - \bhim\b
+  - \bhis\b
+  - \bshe\b
+  - \bher\b

.github/styles/Kedro/headings.yml

@@ -0,0 +1,56 @@
+extends: capitalization
+message: "'%s' should use sentence-style capitalization."
+level: warning
+scope: heading
+match: $sentence
+exceptions:
+  - Kedro
+  - Kedro-Viz
+  - Airflow
+  - Amazon
+  - Amazon Web Services
+  - AWS Step Functions
+  - AWS Systems Manager
+  - Azure
+  - Azure App Service
+  - Azure App Service Plan
+  - Azure Blob Storage
+  - Azure Event Hub
+  - CI/CD
+  - DataCatalog
+  - Data Catalog
+  - Docker
+  - Docker Compose
+  - Docker Swarm
+  - Dockerfile
+  - GitHub
+  - GitHub Actions
+  - Google
+  - Google Analytics
+  - Google Cloud
+  - Google Cloud Functions
+  - GraphQL
+  - Hook
+  - Hooks
+  - IDs
+  - Jenkins
+  - JFrog
+  - JFrog Artifactory
+  - Jira
+  - Kafka
+  - Kubernetes
+  - Kubernetes Engine
+  - Kubernetes Pod
+  - Kubernetes Service
+  - Lambda
+  - Linux
+  - MySQL
+  - Python
+  - QuantumBlack
+  - QuantumBlack Labs
+  - Red Hat
+  - Redis
+  - Slack
+  - Ubuntu
+  - Unix
+  - URLs

.github/styles/Kedro/inclusive.yml

@@ -0,0 +1,12 @@
+extends: substitution
+message: "Use '%s' instead of '%s'."
+ignorecase: true
+level: error
+action:
+  name: replace
+swap:
+  # bad: good
+  'black ?list': 'disallow list|exclude list'
+  'master': primary
+  'slave': secondary
+  'white ?list': 'allow list|include list'

.github/styles/Kedro/links.yml

@@ -0,0 +1,24 @@
+extends: substitution
+message: "Avoid vague text in links like '%s' unless you can pair it with more descriptive text."
+link: 'https://github.com/kedro-org/kedro/wiki/Kedro-documentation-style-guide'
+ignorecase: true
+scope: raw
+nonword: true
+level: error
+
+swap:
+# For the word 'here' in Markdown and HTML links
+  '\[here\]\(.*?\)': 'here'
+  '<a\s*href\s*=\s*".*?".*?>\s*here\s*</a>': 'here'
+
+# For the word 'this' in Markdown and HTML links
+  '\[this\]\(.*?\)': 'this'
+  '<a\s*href\s*=\s*".*?".*?>\s*this\s*</a>': 'this'
+
+# For the word 'page' in Markdown and HTML links
+  '\[page\]\(.*?\)': 'page'
+  '<a\s*href\s*=\s*".*?".*?>\s*page\s*</a>': 'page'
+
+# For the phrase 'this page' in Markdown and HTML links
+  '\[this page\]\(.*?\)': 'this page'
+  '<a\s*href\s*=\s*".*?".*?>\s*this page\s*</a>': 'this page'

.github/styles/Kedro/oxfordcomma.yml

@@ -0,0 +1,6 @@
+extends: existence
+message: "Use the Oxford comma in '%s'."
+scope: sentence
+level: suggestion
+tokens:
+  - '(?:[^,]+,){1,}\s\w+\s(?:and|or)'

.github/styles/Kedro/pronouns.yml

@@ -0,0 +1,11 @@
+extends: existence
+message: "Avoid first-person singular pronouns such as '%s'."
+level: warning
+nonword: true
+tokens:
+  - (?<=^|\s)I(?=\s)
+  - (?<=^|\s)I,(?=\s)
+  - \bI'm\b
+  - (?<=\s)[Mm]e\b
+  - (?<=\s)[Mm]y\b
+  - (?<=\s)[Mm]ine\b

.github/styles/Kedro/quotes.yml

@@ -0,0 +1,10 @@
+extends: existence
+message: Use straight quotes instead of smart quotes.
+level: warning
+nonword: true
+action:
+tokens:
+  - “
+  - ”
+  - ‘
+  - ’

.github/styles/Kedro/sentencelength.yml

@@ -0,0 +1,11 @@
+extends: occurrence
+message: "Try to keep your sentence length to 30 words or fewer."
+level: suggestion
+# Here, we're counting the number of words
+# in a sentence.
+#
+# If there are more than 30, we'll flag it.
+scope: sentence
+ignorecase: false
+max: 30
+token: (\w+)

.github/styles/Kedro/toowordy.yml

@@ -0,0 +1,218 @@
+# Write Good's "Too wordy" rule https://github.com/testthedocs/vale-styles/blob/master/write-good/TooWordy.yml
+extends: existence
+message: "'%s' is too wordy"
+ignorecase: true
+level: warning
+tokens:
+  - a number of
+  - abundance
+  - accede to
+  - accelerate
+  - accentuate
+  - accompany
+  - accomplish
+  - accorded
+  - accrue
+  - acquiesce
+  - acquire
+  - adjacent to
+  - adjustment
+  - admissible
+  - advantageous
+  - adversely impact
+  - advise
+  - aforementioned
+  - aggregate
+  - aircraft
+  - all of
+  - all things considered
+  - alleviate
+  - allocate
+  - along the lines of
+  - already existing
+  - alternatively
+  - amazing
+  - ameliorate
+  - anticipate
+  - apparent
+  - appreciable
+  - as a matter of fact
+  - as a means of
+  - as far as I'm concerned
+  - as of yet
+  - as to
+  - as yet
+  - ascertain
+  - assistance
+  - at the present time
+  - at this time
+  - attain
+  - attributable to
+  - because of the fact that
+  - belated
+  - benefit from
+  - bestow
+  - by means of
+  - by virtue of the fact that
+  - by virtue of
+  - cease
+  - close proximity
+  - commence
+  - comply with
+  - concerning
+  - consequently
+  - consolidate
+  - constitutes
+  - demonstrate
+  - depart
+  - designate
+  - discontinue
+  - due to the fact that
+  - each and every
+  - economical
+  - eliminate
+  - elucidate
+  - employ
+  - endeavor
+  - enumerate
+  - equitable
+  - equivalent
+  - evaluate
+  - evidenced
+  - exclusively
+  - expedite
+  - expend
+  - expiration
+  - facilitate
+  - factual evidence
+  - feasible
+  - finalise
+  - first and foremost
+  - for all intents and purposes
+  - for the most part
+  - for the purpose of
+  - forfeit
+  - formulate
+  - have a tendency to
+  - honest truth
+  - however
+  - if and when
+  - impacted
+  - implement
+  - in a manner of speaking
+  - in a timely manner
+  - in a very real sense
+  - in accordance with
+  - in addition
+  - in all likelihood
+  - in an effort to
+  - in between
+  - in excess of
+  - in lieu of
+  - in light of the fact that
+  - in many cases
+  - in my opinion
+  - in order to
+  - in regard to
+  - in some instances
+  - in terms of
+  - in the case of
+  - in the event that
+  - in the final analysis
+  - in the nature of
+  - in the near future
+  - in the process of
+  - inception
+  - incumbent upon
+  - indicate
+  - indication
+  - initiate
+  - irregardless
+  - is applicable to
+  - is authorised to
+  - is responsible for
+  - it is essential
+  - it seems that
+  - it was
+  - magnitude
+  - maximum
+  - methodology
+  - minimise
+  - modify
+  - monitor
+  - multiple
+  - necessitate
+  - nevertheless
+  - not certain
+  - not many
+  - not often
+  - not unless
+  - not unlike
+  - notwithstanding
+  - null and void
+  - numerous
+  - objective
+  - obligate
+  - obtain
+  - on the contrary
+  - on the other hand
+  - one particular
+  - optimum
+  - overall
+  - owing to the fact that
+  - participate
+  - particulars
+  - pass away
+  - pertaining to
+  - point in time
+  - portion
+  - possess
+  - preclude
+  - previously
+  - prior to
+  - prioritise
+  - procure
+  - proficiency
+  - provided that
+  - purchase
+  - put simply
+  - readily apparent
+  - refer back
+  - regarding
+  - relocate
+  - remainder
+  - remuneration
+  - requirement
+  - reside
+  - residence
+  - retain
+  - satisfy
+  - shall
+  - should you wish
+  - similar to
+  - solicit
+  - span across
+  - strategise
+  - subsequent
+  - substantial
+  - successfully complete
+  - sufficient
+  - terminate
+  - the month of
+  - the point I am trying to make
+  - therefore
+  - time period
+  - took advantage of
+  - transmit
+  - transpire
+  - type of
+  - until such time as
+  - utilisation
+  - utilise
+  - validate
+  - various different
+  - what I mean to say is
+  - whether or not
+  - with respect to
+  - with the exception of
+  - witnessed