Class: Censive
- Inherits:
-
StringScanner
- Object
- StringScanner
- Censive
- Defined in:
- lib/censive.rb
Constant Summary collapse
- VERSION =
"1.0.3"
Instance Attribute Summary collapse
-
#encoding ⇒ Object
readonly
Returns the value of attribute encoding.
-
#out ⇒ Object
readonly
Returns the value of attribute out.
-
#rows ⇒ Object
readonly
Returns the value of attribute rows.
Class Method Summary collapse
Instance Method Summary collapse
-
#<<(row) ⇒ Object
output a row.
- #bomb(msg) ⇒ Object
- #each ⇒ Object
-
#grok(str) ⇒ Object
returns 2 (must be quoted and escaped), 1 (must be quoted), 0 (neither).
-
#initialize(str = nil, drop: false, encoding: nil, excel: false, mode: :compact, out: nil, quote: '"', relax: false, rowsep: "\n", sep: ",", strip: false, **opts) {|_self| ... } ⇒ Censive
constructor
A new instance of Censive.
- #next_row ⇒ Object
- #next_token ⇒ Object
-
#parse ⇒ Object
[ Parser ]==.
- #reset(str = nil) ⇒ Object
- #stats ⇒ Object
- #to_csv(*args, **opts, &code) ⇒ Object
Constructor Details
#initialize(str = nil, drop: false, encoding: nil, excel: false, mode: :compact, out: nil, quote: '"', relax: false, rowsep: "\n", sep: ",", strip: false, **opts) {|_self| ... } ⇒ Censive
Returns a new instance of Censive.
48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
# File 'lib/censive.rb', line 48 def initialize(str=nil, drop: false , # drop trailing empty columns? encoding: nil , # character encoding excel: false , # literals ="01" formulas =A1 + B2 http://bit.ly/3Y7jIvc mode: :compact, # output mode: compact or full out: nil , # output stream, needs to respond to << quote: '"' , # quote character relax: false , # relax quote parsing so ,"Fo"o, => ,"Fo""o", rowsep: "\n" , # row separator for output sep: "," , # column separator character strip: false , # strip columns when reading **opts # grab bag ) # initialize data source if str && str.size < 100 && File.readable?(str) str = File.open(str, encoding ? "r:#{encoding}" : "r").read else str ||= "" str = str.encode(encoding) if encoding end super(str) reset # config options @cheat = true @drop = drop @encoding = str.encoding @excel = excel @mode = mode @out = out || $stdout @relax = relax @strip = strip # config strings @quote = quote @rowsep = rowsep @sep = sep # static strings @cr = "\r" @lf = "\n" @es = "" @eq = "=" # combinations @esc = (@quote * 2) @seq = [@sep, @eq].join # used for parsing in excel mode # regexes xsep = Regexp.escape(@sep) # may need to be escaped @eoc = /(?=#{"\\" + xsep}|#{@cr}|#{@lf}|\z)/o # end of cell @eol = /#{@cr}#{@lf}?|#{@lf}/o # end of line @escapes = /(#{@quote})|#{xsep}|#{@cr}|#{@lf}/o @quotable = /#{xsep}|#{@cr}|#{@lf}/o @quotes = /#{@quote}/o @seps = /#{xsep}+/o @quoted = @excel ? /(?:=)?#{@quote}/o : @quote @unquoted = /[^#{xsep}#{@cr}#{@lf}][^#{@quote}#{@cr}#{@lf}]*/o @leadzero = /\A0\d*\z/ yield self if block_given? end |
Instance Attribute Details
#encoding ⇒ Object (readonly)
Returns the value of attribute encoding.
34 35 36 |
# File 'lib/censive.rb', line 34 def encoding @encoding end |
#out ⇒ Object (readonly)
Returns the value of attribute out.
34 35 36 |
# File 'lib/censive.rb', line 34 def out @out end |
#rows ⇒ Object (readonly)
Returns the value of attribute rows.
34 35 36 |
# File 'lib/censive.rb', line 34 def rows @rows end |
Class Method Details
.parse ⇒ Object
36 37 38 |
# File 'lib/censive.rb', line 36 def self.parse(...) new(...).parse end |
.writer(obj = nil, **opts, &code) ⇒ Object
40 41 42 43 44 45 46 |
# File 'lib/censive.rb', line 40 def self.writer(obj=nil, **opts, &code) case obj when String then File.open(obj, "w") {|io| new(out: io, **opts, &code) } when StringIO,IO,nil then new(out: obj, **opts, &code) else abort "#{File.basename($0)}: invalid #{obj.class} object in writer" end end |
Instance Method Details
#<<(row) ⇒ Object
output a row
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 |
# File 'lib/censive.rb', line 211 def <<(row) # drop trailing empty columns row.pop while row.last.empty? if @drop s,q = @sep, @quote out = case @mode when :compact case @excel ? 2 : grok(row.join) when 0 row when 1 row.map do |col| col&.match?(@quotable) ? "#{q}#{col}#{q}" : col end else row.map do |col| @excel && col =~ @leadzero ? "=#{q}#{col}#{q}" : case grok(col) when 0 then col when 1 then "#{q}#{col}#{q}" else "#{q}#{col.gsub(q, @esc)}#{q}" end end end when :full if @excel row.map do |col| col =~ @leadzero ? "=#{q}#{col}#{q}" : "#{q}#{col.gsub(q, @esc)}#{q}" end else row.map {|col| "#{q}#{col.gsub(q, @esc)}#{q}" } end end.join(s) @out << out + @rowsep end |
#bomb(msg) ⇒ Object
257 258 259 |
# File 'lib/censive.rb', line 257 def bomb(msg) abort "\n#{File.basename($0)}: #{msg} at character #{pos} near '#{string[pos-4,7]}'" end |
#each ⇒ Object
184 185 186 187 |
# File 'lib/censive.rb', line 184 def each @rows or parse @rows.each {|row| yield row } end |
#grok(str) ⇒ Object
returns 2 (must be quoted and escaped), 1 (must be quoted), 0 (neither)
202 203 204 205 206 207 208 |
# File 'lib/censive.rb', line 202 def grok(str) if idx = str&.index(@escapes) $1 ? 2 : str.index(@quote, idx) ? 2 : 1 else 0 end end |
#next_row ⇒ Object
133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 |
# File 'lib/censive.rb', line 133 def next_row if @cheat and line = scan_until(@eol) row = line.chomp!.split(@sep, -1) row.each do |col| next if (saw = col.count(@quote)).zero? next if (saw == 2) && col.delete_prefix!(@quote) && col.delete_suffix!(@quote) @cheat = false break end if line.include?(@quote) @cheat and return @strip ? row.each(&:strip!) : row unscan end token = next_token or return row = [] row.push(*token) row.push(*token) while token = next_token row end |
#next_token ⇒ Object
153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 |
# File 'lib/censive.rb', line 153 def next_token if scan(@quoted) # quoted cell token = "" while true token << (scan_until(@quotes) or bomb "unclosed quote")[0..-2] token << @quote and next if scan(@quote) scan(@eoc) and break @relax or bomb "invalid character after quote" token << @quote + (scan_until(@quotes) or bomb "bad inline quote") scan(@eoc) and break end scan(@sep) @strip ? token.strip : token elsif match = scan(@unquoted) # unquoted cell(s) if check(@quote) && !match.chomp!(@sep) # if we see a stray quote unless @excel && match.chomp!(@seq) # unless an excel literal, fix it match << (scan_until(@eoc) or bomb "stray quote") scan(@sep) end end tokens = match.split(@sep, -1) @strip ? tokens.map!(&:strip) : tokens elsif scan(@sep) match = scan(@seps) match ? match.split(@sep, -1) : @es else scan(@eol) nil end end |
#parse ⇒ Object
[ Parser ]==
122 123 124 125 126 127 128 129 130 131 |
# File 'lib/censive.rb', line 122 def parse @rows = [] while row = next_row @rows << row count = row.size @cols = count if count > @cols @cells += count end self end |
#reset(str = nil) ⇒ Object
111 112 113 114 115 116 117 118 |
# File 'lib/censive.rb', line 111 def reset(str=nil) @rows = nil @cols = @cells = 0 self.string = str if str @encoding = string.encoding super() end |
#stats ⇒ Object
249 250 251 252 253 254 255 |
# File 'lib/censive.rb', line 249 def stats wide = string.size.to_s.size puts "%#{wide}d rows" % @rows.size puts "%#{wide}d columns" % @cols puts "%#{wide}d cells" % @cells puts "%#{wide}d bytes" % string.size end |
#to_csv(*args, **opts, &code) ⇒ Object
189 190 191 192 193 194 195 196 197 |
# File 'lib/censive.rb', line 189 def to_csv(*args, **opts, &code) if args.empty? && opts.empty? block_given? ? each(&code) : each {|row| @out << row } elsif block_given? Censive.writer(*args, **opts, &code) else Censive.writer(*args, **opts) {|csv| each {|row| csv << row }} end end |