pretty/test/test_pstring.lua

local SUITE = require 'TestSuite' 'string'
SUITE:setEnviroment{
    format  = require('pretty')
}

--------------------------------------------------------------------------------

-- Compat
if not loadstring then  loadstring = load  end                        -- Lua 5.3 compat
--

local function format_test (t)
    SUITE:addTest(t.name or t.expect, function ()
        assert_equal(t.expect, format(t.input, t.options))
    end, { line = debug.getinfo(2).currentline })

    if not t.not_idempotent then
        -- Additional parsable test
        SUITE:addTest((t.name or t.expect) .. ' (parsable?)', function ()
            local chunk, error_msg  =  loadstring('return '..format(t.input, t.options))
            if not chunk then  error(error_msg)  end
        end, { line = debug.getinfo(2).currentline })
        -- Additional idempotent test
        SUITE:addTest((t.name or t.expect) .. ' (idempotent?)', function ()
            local output  =  loadstring('return '..format(t.input, t.options))()
            assert_equal(t.input, output)
        end, { line = debug.getinfo(2).currentline })
    end
end

--------------------------------------------------------------------------------
-- Shortform Strings

format_test {
    input  = 'Hello World',
    expect = '\'Hello World\'',
}

format_test {
    input  = 'Hello \'World\'',
    expect = '\'Hello \\\'World\\\'\'',
}

format_test {
    input  = 'Hello \"World\"',
    expect = '\'Hello \"World\"\'',
}

format_test {
    input  = 'Hello [[World]]',
    expect = '\'Hello [[World]]\'',
}

format_test {
    input  = '\'Hello\' [[World]]',
    expect = '\'\\\'Hello\\\' [[World]]\'',
}

format_test {
    input  = '\'Hello\' \"there\" [[World]]',
    expect = '\'\\\'Hello\\\' \"there\" [[World]]\'',
}

format_test {
    input  = '\'Hello\' \"there\" [=[World]=]',
    expect = '\'\\\'Hello\\\' \"there\" [=[World]=]\'',
}

format_test {
    input  = '\nHello World',
    expect = [['\nHello World']],
}

format_test {
    input  = '\'\"\n',
    expect = [['\'"\n']],
}

format_test {
    input  = '\n',
    expect = '\'\\n\'',
}

format_test {
    input  = '\\',
    expect = [['\\']],
}

format_test {
    input  = '\000',
    expect = '\'\\000\'',
}

format_test {
    input  = '\a\b\v\r\f',
    expect = [['\a\b\v\r\f']],
}

--------------------------------------------------------------------------------
-- Cut Strings

format_test {
    name   = 'Cut string basics',
    not_idempotent = true,
    input  = {'Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nunc vestibulum tempus ligula. Sed ac lobortis mi.'},
    expect = '{\n    \'Lorem ipsum dolor sit amet, consectet\'...\n}',
}

format_test {
    name   = 'Cut strings are cut after escaping',
    not_idempotent = true,
    input  = {'Lorem\tipsum\tdolor\tsit\tamet,\tconsectetur\tadipiscing\telit.\tNunc\tvestibulum\ttempus\tligula.\tSed\tac\tlobortis\tmi.'},
    expect = '{\n    \'Lorem\\tipsum\\tdolor\\tsit\\tamet,\\tcons\'...\n}',
}

format_test {
    name   = 'Cut strings are cut after escaping 2',
    not_idempotent = true,
    input  = {'Lorem ipsum dolor sit amet, conse\t\t\tctetur adipiscing elit. Nunc vestibulum tempus ligula. Sed ac lobortis mi.'},
    expect = '{\n    \'Lorem ipsum dolor sit amet, conse\\t\\t\'...\n}',
}

format_test {
    name   = 'Cut strings are not cut in the middle of an escape code',
    not_idempotent = true,
    input  = {'Lorem ipsum dolor sit amet, consec\t\t\ttetur adipiscing elit. Nunc vestibulum tempus ligula. Sed ac lobortis mi.'},
    expect = '{\n    \'Lorem ipsum dolor sit amet, consec\\t\'...\n}',
}

format_test {
    name   = 'Cut strings are not cut in the middle of escaping \\',
    not_idempotent = true,
    input  = {'Lorem ipsum dolor sit amet, conse\\\\\\\\ctetur adipiscing elit. Nunc vestibulum tempus ligula. Sed ac lobortis mi.'},
    expect = '{\n    \'Lorem ipsum dolor sit amet, conse\\\\\\\\\'...\n}',
}

format_test {
    name   = 'Cut strings are not cut in the middle of decimal escape codes',
    not_idempotent = true,
    input  = {'Lorem ipsum dolor sit amet, consect\014etur adipiscing elit. Nunc vestibulum tempus ligula. Sed ac lobortis mi.'},
    expect = '{\n    \'Lorem ipsum dolor sit amet, consect\'...\n}',
}

format_test {
    -- NOTE: Not priority functionallity.
    name   = 'Cut strings can shorten decimal escape codes, if nessesary and possible',
    not_idempotent = true,
    input  = {'Lorem ipsum dolor sit amet, consec\014tetur adipiscing elit. Nunc vestibulum tempus ligula. Sed ac lobortis mi.'},
    expect = '{\n    \'Lorem ipsum dolor sit amet, consec\\14\'...\n}',
}

--------------------------------------------------------------------------------
-- Concatted Strings

format_test {
    name   = 'Concatted string basics',
    input  = 'Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nunc vestibulum tempus ligula. Sed \004\002\000 ac lobortis mi.',
    expect = [['Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nunc vestibulum te' ..]]..'\n'..[['mpus ligula. Sed \004\002\000 ac lobortis mi.']],
}

format_test {
    name   = 'Concatted string basics 2',
    input  = 'Lorem ipsum dolor sit amet, consectetur adipiscing elit.\004\002\000Nunc vestibulum tempus ligula. Sed ac lobortis mi.',
    expect = [['Lorem ipsum dolor sit amet, consectetur adipiscing elit.\004\002\000Nunc ve' ..]]..'\n'..[['stibulum tempus ligula. Sed ac lobortis mi.']],
}


--------------------------------------------------------------------------------
-- Longform Strings

local LONG_STRING = [[
Lorem ipsum dolor sit amet, consectetur adipiscing elit.
Nunc vestibulum tempus ligula. Sed ac lobortis mi.
Morbi eu arcu id nunc cursus auctor. Nulla enim tortor, sodales ut nunc non,
euismod aliquam libero. Aliquam neque est, iaculis in nibh vel, mollis ultricies
ante. Sed egestas et massa sit amet posuere. Integer at suscipit lorem, non
consectetur lacus. Vivamus ac facilisis sem. Proin lacinia ex eu volutpat
interdum.
]]

format_test {
    name   = 'Longform string basics',
    input  = LONG_STRING,
    expect = '[[\n'..LONG_STRING..']]'
}

local LONG_STRING_WITH_LEVELS = [=[
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nunc vestibulum tempus
ligula. Sed ac lobortis mi. [Morbi eu arcu id nunc cursus auctor. [Nulla enim
tortor, sodales ut nunc non, euismod aliquam libero.]] Aliquam neque est,
iaculis in nibh vel, mollis ultricies ante. Sed egestas et massa sit amet
posuere. Integer at suscipit lorem, non consectetur lacus. Vivamus ac facilisis
sem. Proin lacinia ex eu volutpat interdum.
]=]

format_test {
    name   = 'Longform string that requires level 1',
    input  = LONG_STRING_WITH_LEVELS,
    expect = '[=[\n'..LONG_STRING_WITH_LEVELS..']=]'
}

local LONG_STRING_WITH_HIGH_LEVELS = [[
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nunc vestibulum tempus
ligula. Sed ac lobortis mi. [=[Morbi eu arcu id nunc cursus auctor. [Nulla enim
tortor, sodales ut nunc non, euismod aliquam libero.]=] Aliquam neque est,
iaculis in nibh vel, mollis ultricies ante. Sed egestas et massa sit amet
posuere. Integer at suscipit lorem, non consectetur lacus. Vivamus ac facilisis
sem. Proin lacinia ex eu volutpat interdum.
]]

format_test {
    name   = 'Longform string that requires level 0, but not 1',
    input  = LONG_STRING_WITH_HIGH_LEVELS,
    expect = '[[\n'..LONG_STRING_WITH_HIGH_LEVELS..']]'
}

--------------------------------------------------------------------------------
-- Unicode

format_test {
    input  = 'ø',
    expect = '\'ø\'',
}

format_test {
    name   = 'Single utf8 continuation byte is escaped',
    input  = 'abc\169def',
    expect = '\'abc\\169def\'',
}

format_test {
    name   = 'Multiple utf8 continuation bytes are escaped',
    input  = 'abc\169\190\169\169def',
    expect = '\'abc\\169\\190\\169\\169def\'',
}

format_test {
    name   = 'Single start byte utf8 chars is escaped',
    input  = 'abc\255def',
    expect = '\'abc\\255def\'',
}

-- TODO: Add more malformed unicode tests: https://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt

--------------------------------------------------------------------------------

return SUITE