settings.json

{
  "options": [{
      "key": "normalize_eol",
      "label": "Normalize eol",
      "description": [
        "replaces windows end of lines with unix eol (`\n`)"
      ],
      "default": true
    },
    {
      "key": "decode_htmlentities",
      "label": "Decode HTML Entities",
      "description": [
        "converts numeral and selected html character-sets into original characters"
      ],
      "default": true
    },
    {
      "key": "fix_dashes",
      "label": "Fix Dashes",
      "description": [
        "replaces triple dash to mdash",
        "replaces double dash to ndash"
      ],
      "default": true
    },
    {
      "key": "fix_three_dots",
      "label": "Fix three dots",
      "description": [
        "removes spaces between dots",
        "replaces three dots with ellipsis character"
      ],
      "default": true
    },
    {
      "key": "normalize_ellipsis",
      "label": "Normalize Ellipsis",
      "description": [
        "replaces more than one ellipsis with one",
        "replaces (space|tab|zwnj) after ellipsis with one space"
      ],
      "default": true
    },
    {
      "key": "normalize_dates",
      "label": "Normalize Dates",
      "description": [
        "re-orders date parts with slash as delimiter"
      ],
      "default": true
    },
    {
      "key": "fix_english_quotes_pairs",
      "label": "Fix English Quotes Pairs",
      "description": [
        "replaces english quote pairs with their persian equivalent"
      ],
      "default": true
    },
    {
      "key": "fix_english_quotes",
      "label": "Fix English Quotes",
      "description": [
        "replaces english quote marks with their persian equivalent"
      ],
      "default": true
    },
    {
      "key": "fix_hamzeh",
      "label": "Fix Hamzeh",
      "description": [
        "replaces ه followed by (space|ZWNJ|lrm) follow by ی with هٔ",
        "replaces ه followed by (space|ZWNJ|lrm|nothing) follow by ء with هٔ",
        "replaces هٓ or single-character ۀ with the standard هٔ"
      ],
      "default": true
    },
    {
      "key": "fix_hamzeh_arabic",
      "label": "Fix Hamzeh Arabic",
      "description": [
        "converts arabic hamzeh ة to هٔ"
      ],
      "default": false
    },
    {
      "key": "cleanup_rlm",
      "label": "Cleanup RLM",
      "description": [
        "converts Right-to-left marks followed by persian characters to zero-width non-joiners (ZWNJ)"
      ],
      "default": true
    },
    {
      "key": "cleanup_zwnj",
      "label": "Cleanup ZWNJ",
      "description": [
        "converts all soft hyphens (­) into zwnj",
        "removes more than one zwnj",
        "cleans zwnj after characters that don't conncet to the next",
        "cleans zwnj before and after numbers, english words, spaces and punctuations",
        "removes unnecessary zwnj on start/end of each line"
      ],
      "default": true
    },
    {
      "key": "fix_spacing_for_braces_and_quotes",
      "label": "Fix Spacing for Braces and Quotes",
      "description": [
        "removes inside spaces and more than one outside for `()`, `[]`, `{}`, `“”` and `«»`"
      ],
      "default": true
    },
    {
      "key": "fix_arabic_numbers",
      "label": "Fix Arabic Numbers",
      "description": [
        "replaces arabic numbers with their persian equivalent"
      ],
      "default": true
    },
    {
      "key": "fix_english_numbers",
      "label": "Fix English Numbers",
      "description": [
        "replaces english numbers with their persian equivalent"
      ],
      "default": true
    },
    {
      "key": "fix_misc_non_persian_chars",
      "label": "Fix Misc Non-Persian Chars",
      "description": [
        "replaces arabic normal/swash kaf with its persian equivalent",
        "replaces arabic/urdu/pushtu/uyghur yeh with its persian equivalent",
        "replaces kurdish he with its persian equivalent"
      ],
      "default": true
    },
    {
      "key": "fix_punctuations",
      "label": "Fix Punctuations",
      "description": [
        "replaces `,`, `;` with its persian equivalent"
      ],
      "default": true
    },
    {
      "key": "fix_question_mark",
      "label": "Fix Question Marks",
      "description": [
        "replaces question marks with its persian equivalent"
      ],
      "default": true
    },
    {
      "key": "skip_markdown_ordered_lists_numbers_conversion",
      "label": "Skip Markdown Ordered Lists Numbers Conversion",
      "description": [
        "skips converting english numbers of ordered lists in markdown"
      ],
      "default": false
    },
    {
      "key": "fix_perfix_spacing",
      "label": "Fix Perfix Spacing",
      "description": [
        "puts zwnj between the word and the prefix: `mi*`, `nemi*`, `bi*`"
      ],
      "default": true
    },
    {
      "key": "fix_suffix_spacing",
      "label": "Fix Suffix Spacing",
      "description": [
        "put zwnj between word and suffix: `*am`, `*at`, `*ash`, `*ei`, `*eid`, `*eem`, `*and`, `*man`, `*tan`, `*shan`, `*ha`, `*haye`, `*tar`, `*tari`, `*tarin`, `*hayee`, `*hayam`, `*hayat`, `*hayash`, `*hayetan`, `*hayeman`, `*hayeshan`"
      ],
      "default": true
    },
    {
      "key": "fix_suffix_misc",
      "label": "Fix Suffix Misc",
      "description": [
        "replaces `ه` followed by `ئ` or `ی`, and then by `ی`, with `ه‌ای`"
      ],
      "default": true
    },
    {
      "key": "kashidas_as_parenthetic",
      "label": "Kashidas as Parenthetic",
      "description": [
        "replaces kashidas to ndash in parenthetic"
      ],
      "default": true
    },
    {
      "key": "cleanup_kashidas",
      "label": "Cleanup Kashidas",
      "description": [
        "converts kashida between numbers to ndash",
        "removes all kashidas between non-whitespace characters"
      ],
      "default": true
    },
    {
      "key": "cleanup_extra_marks",
      "label": "Cleanup Extra Marks",
      "description": [
        "removes space between different/same marks",
        "replaces more than one exclamation mark with just one",
        "replaces more than one english or persian question mark with just one",
        "re-orders consecutive marks: `?!` into `!?`"
      ],
      "default": true
    },
    {
      "key": "cleanup_spacing",
      "label": "Cleanup Spacing",
      "description": [
        "replaces more than one space with just a single one",
        "cleans whitespace/zwnj between new-lines"
      ],
      "default": true
    },
    {
      "key": "cleanup_line_breaks",
      "label": "Cleanup Line Breaks",
      "description": [
        "cleans more than *two* contiguous line breaks"
      ],
      "default": true
    },
    {
      "key": "cleanup_begin_and_end",
      "label": "Cleanup Begin and End",
      "description": [
        "removes space/tab/zwnj/nbsp from the beginning of the new-lines",
        "removes spaces, tabs, zwnj, direction marks and new lines from the beginning and end of text"
      ],
      "default": true
    },
    {
      "key": "preserve_HTML",
      "label": "Preserve HTML",
      "description": [
        "preserves all html tags in the text"
      ],
      "default": true
    },
    {
      "key": "preserve_comments",
      "label": "Preserve Comments",
      "description": [
        "preserves all html comments in the text"
      ],
      "default": true
    },
    {
      "key": "preserve_entities",
      "label": "Preserve Entities",
      "description": [
        "preserves all html entities in the text"
      ],
      "default": true
    },
    {
      "key": "preserve_frontmatter",
      "label": "Preserve Frontmatter",
      "description": [
        "preserves frontmatter data in the text"
      ],
      "default": true
    },
    {
      "key": "preserve_URIs",
      "label": "Preserve URIs",
      "description": [
        "preserves all uri strings in the text"
      ],
      "default": true
    },
    {
      "key": "preserve_nbsps",
      "label": "Preserve NBSPs",
      "description": [
        "preserves all no-break space entities in the text"
      ],
      "default": true
    },
    {
      "key": "preserve_brackets",
      "label": "Preserve Brackets",
      "description": [
        "preserves strings inside square brackets (`[]`)"
      ],
      "default": false
    },
    {
      "key": "preserve_braces",
      "label": "Preserve Braces",
      "description": [
        "preserves strings inside curly braces (`{}`)"
      ],
      "default": false
    },
    {
      "key": "fix_diacritics",
      "label": "Fix Diacritics",
      "description": [
        "cleans zwnj before diacritic characters",
        "cleans more than one diacritic characters",
        "cleans spaces before diacritic characters"
      ],
      "default": true
    },
    {
      "key": "remove_diacritics",
      "label": "Remove Diacritics",
      "description": [
        "removes all diacritic characters"
      ],
      "default": false
    },
    {
      "key": "fix_numeral_symbols",
      "label": "Fix Numeral Symbols",
      "description": [
        "replaces english percent signs (U+066A)",
        "replaces dots between numbers into decimal separator (U+066B)",
        "replaces commas between numbers into thousands separator (U+066C)"
      ],
      "default": true
    },
    {
      "key": "fix_persian_glyphs",
      "label": "Fix Persian Glyphs",
      "description": [
        "converts incorrect persian glyphs to standard characters"
      ],
      "default": true
    },
    {
      "key": "fix_misc_spacing",
      "label": "Fix Misc Spacing",
      "description": [
        "removes space before parentheses on misc cases",
        "removes space before braces containing numbers"
      ],
      "default": true
    },
    {
      "key": "fix_spacing_for_punctuations",
      "label": "Fix Spacing for Punctuations",
      "description": [
        "removes space before punctuations",
        "removes more than one space after punctuations, except followed by new-lines",
        "removes space after colon that separates time parts",
        "removes space after dots in numbers",
        "removes space before some common domain tlds",
        "removes space between different/same marks"
      ],
      "default": true
    },
    {
      "key": "markdown_normalize_braces",
      "label": "Markdown Normalize Braces",
      "description": [
        "removes spaces between `[]` and `()` (`[text] (link)` into `[text](link)`)",
        "removes space between `!` and opening brace (`! [alt](src)` into `![alt](src)`)",
        "removes spaces inside double `()`, `[]`, `{}` (`[[ text ]]` into `[[text]]`)",
        "removes spaces between double `()`, `[]`, `{}` (`[[text] ]` into `[[text]]`)"
      ],
      "default": true
    },
    {
      "key": "markdown_normalize_lists",
      "label": "Markdown Normalize Lists",
      "description": [
        "removes extra lines between two items on a markdown list beginning with `-`, `*` or `#`"
      ],
      "default": true
    }
  ]
}