struct Hyoki::Document

• Hyoki::Document
• Struct
• Value
• Object

Defined in:

hyoki.cr

Constant Summary

ASCII_WORD_REGEX = /\A[[:ascii:]]+\z/

LINE_REGEX = /([^\r\n]*?)(\r\n|\r|\n)|(.+)/

TSV_ESCAPE = {"\n" => "\\n", "\t" => "\\t", "\r" => "\\r", "\\" => "\\\\"}

TSV_ESCAPE_REGEX = Regex.new(TSV_ESCAPE.keys.map do |k| "(?:#{Regex.escape(k)})" end.join("|"))

TSV_HEADER_HETERONYMS = ["surface", "source", "line", "character", "yomi", "surface", "excerpt"].join("\t")

TSV_HEADER_VARIANTS = ["lexical form yomi", "source", "line", "character", "lexical form", "surface", "excerpt"].join("\t")

Constructors

• .new(source_ios : Array(IO), mecab_dict_dir = nil)
• .new(string : String, mecab_dict_dir = nil)

Instance Method Summary

• #excerpt(morpheme, context_length, highlight = nil)
• #heteronyms(lines, sort_order, include_ascii) : ReportItems

  Returns an associative list of surface expression to heteronyms: words with same spelling and different pronunciation.

• #items_to_markdown(items, excerpt_context_length, highlight, &)
• #items_to_text(items, excerpt_context_length, highlight, &)
• #items_to_tsv(items, excerpt_context_length, highlight, header, &)
• #lines : Array(Hyoki::Document::Line)
• #markup_as_markdown_inline_code(string)
• #report(type = ReportType::Variants, format = ReportFormat::Text, excerpt_context_length = 5, sort_order = SortOrder::Alphabetical, highlight = false, header = nil, include_ascii = true)
• #report_heteronyms(format, excerpt_context_length, sort_order, highlight, header, include_ascii)
• #report_variants(format, excerpt_context_length, sort_order, highlight, header, include_ascii)
• #variants(lines, yomi_parser, sort_order, include_ascii) : ReportItems

  Returns an associative list of yomi (of dictionary form) to variants: words with same pronunciation and different spelling.

Constructor Detail

Instance Method Detail