Module: RemoteTable::Format::Textual

Included in:
Delimited, FixedWidth, HTML, XML
Defined in:
lib/remote_table/format/mixins/textual.rb

Constant Summary collapse

USELESS_CHARACTERS = 
[
  '\xef\xbb\xbf',   # UTF-8 byte order mark
  '\xc2\xad',       # soft hyphen, often inserted by MS Office (html: ­)
  '\xad',
  # '\xa0'
]

Instance Method Summary collapse

Instance Method Details

#crop_rows! ⇒ Object 



21
22
23
24
 
# File 'lib/remote_table/format/mixins/textual.rb', line 21

def crop_rows!
  return unless t.properties.crop
  ::RemoteTable.executor.bang t.local_file.path, "tail -n +#{::Escape.shell_single_word t.properties.crop.first.to_s} | head -n #{t.properties.crop.last - t.properties.crop.first + 1}"
end

#cut_columns! ⇒ Object 



26
27
28
29
 
# File 'lib/remote_table/format/mixins/textual.rb', line 26

def cut_columns!
  return unless t.properties.cut
  ::RemoteTable.executor.bang t.local_file.path, "cut -c #{::Escape.shell_single_word t.properties.cut.to_s}"
end

#remove_useless_characters! ⇒ Object

‘xa0’



12
13
14
 
# File 'lib/remote_table/format/mixins/textual.rb', line 12

def remove_useless_characters!
  ::RemoteTable.executor.bang t.local_file.path, "perl -pe 's/#{USELESS_CHARACTERS.join '//g; s/'}//g'"
end

#skip_rows! ⇒ Object 



16
17
18
19
 
# File 'lib/remote_table/format/mixins/textual.rb', line 16

def skip_rows!
  return unless t.properties.skip > 0
  ::RemoteTable.executor.bang t.local_file.path, "tail -n +#{t.properties.skip + 1}"
end