.pyspelling.yml

# This will instruct pyspelling to perform spell check on
#    - Static HTML files in "public" directory (except for WET files)
#    - gcweb and gcintranet wet-messages-*.json, files:
#        - For english, the "source" property
#        - For french, the "target" property
#      (note that is both cases values containing '<', '>' or '-' will be skipped)
#
# ref: https://facelessuser.github.io/pyspelling/pipeline/
matrix:
- name: messages-en
  sources:
  - 'src/gcweb/wet-messages.en.json'
  - 'src/gcintranet/wet-messages.en.json'
  aspell:
    lang: en
    d: en_CA
    #filter-path: /mingw64/lib/aspell-0.60
  dictionary:
    wordlists:
    - spell-wordlist-en.txt
    output: tmp/wordlist-en.dic
    encoding: utf-8
  pipeline:
  - pyspelling.filters.context:
      context_visible_first: false
      delimiters:
      # In an attempt to skip values containing HTML or file names, the
      # open token is basically any `"source": "` that is NOT followed at some point by a `<` or a `-`
      # The URLs will be filtered out by next pipeline step
      - open: '^\s*"source":\s*"(?!.*[\-\<\>])'
        close: '",$'
  - pyspelling.filters.url:
- name: messages-fr
  sources:
  - 'src/gcweb/wet-messages.fr.json'
  - 'src/gcintranet/wet-messages.fr.json'
  aspell:
    lang: fr
    #d: fr_CA
    #filter-path: /mingw64/lib/aspell-0.60
  dictionary:
    wordlists:
    - spell-wordlist-fr.txt
    output: tmp/wordlist-fr.dic
    encoding: utf-8
  pipeline:
  - pyspelling.filters.context:
      context_visible_first: false
      delimiters:
      # In an attempt to skip values containing HTML or file names, the
      # open token is basically any `"target": "` that is NOT followed at some point by a `<` or a `-`
      # The URLs will be filtered out by next pipeline step
      - open: '^\s*"target":\s*"(?!.*[\-\<\>])'
        close: '"$'
  - pyspelling.filters.url:
- name: HTML-EN
  sources:
  - 'public/common/**/*-en.html'
  - 'public/common/**/*-eng.html'
  - 'public/gcweb/**/*-en.html'
  - 'public/gcweb/**/*-eng.html'
  - 'public/gcintranet/**/*-en.html'
  - 'public/gcintranet/**/*-eng.html'
  - 'public/global/**/*-en.html'
  - 'public/global/**/*-eng.html'
  expect_match: false  #no error is no file found
  default_encoding: utf-8
  aspell:
    lang: en
    d: en_CA
    #filter-path: /mingw64/lib/aspell-0.60
  dictionary:
    wordlists:
    - spell-wordlist-en.txt
    output: tmp/wordlist-en.dic
    encoding: utf-8
  pipeline:
  - pyspelling.filters.html:
      comments: false # We have a lot of paths and other stuff in out HTML comments, truning spell check off
      attributes:
      - title
      - alt
      ignores:
      - ':matches(code, pre)'
      - 'code'
      - 'pre'
- name: HTML-FR
  sources:
  - 'public/common/**/*-fr.html'
  - 'public/common/**/*-fra.html'
  - 'public/gcweb/**/*-fr.html'
  - 'public/gcweb/**/*-fra.html'
  - 'public/gcintranet/**/*-fr.html'
  - 'public/gcintranet/**/*-fra.html'
  - 'public/global/**/*-fr.html'
  - 'public/global/**/*-fra.html'
  expect_match: false  #no error is no file found
  default_encoding: utf-8
  aspell:
    lang: fr
    #d: fr_CA
    #filter-path: /mingw64/lib/aspell-0.60
  dictionary:
    wordlists:
    - spell-wordlist-fr.txt
    output: tmp/wordlist-fr.dic
    encoding: utf-8
  pipeline:
  - pyspelling.filters.html:
      comments: false # We have a lot of paths and other stuff in out HTML comments, truning spell check off
      attributes:
      - title
      - alt
      ignores:
      - ':matches(code, pre)'
      - 'code'
      - 'pre'
#- name: markdown-en
#  sources:
#  #- '**/*.md|!*-fr.md'
#  - '*.md|!*-fr.md'
#  aspell:
#    lang: en
#    d: en_CA
#    #filter-path: /mingw64/lib/aspell-0.60
#  dictionary:
#    wordlists:
#    - spell-wordlist-en.txt
#    output: tmp/wordlist-en.dic
#    encoding: utf-8
#  pipeline:
#  - pyspelling.filters.markdown:
#      markdown_extensions:
#      - markdown.extensions.extra:
#  - pyspelling.filters.html:
#      comments: true
#      attributes:
#      - title
#      - alt
#      ignores:
#      - :matches(code, pre, samp, kbd, var)