1
0
Fork 0
mirror of https://github.com/jashkenas/coffeescript.git synced 2022-11-09 12:23:24 -05:00
jashkenas--coffeescript/test/location.coffee
Simon Lydell 0dcff507fb Refactor interpolation (and string and regex) handling in lexer
- Fix #3394: Unclosed single-quoted strings (both regular ones and heredocs)
  used to pass through the lexer, causing a parsing error later, while
  double-quoted strings caused an error already in the lexing phase. Now both
  single and double-quoted unclosed strings error out in the lexer (which is the
  more logical option) with consistent error messages. This also fixes the last
  comment by @satyr in #3301.

- Similar to the above, unclosed heregexes also used to pass through the lexer
  and not error until in the parsing phase, which resulted in confusing error
  messages. This has been fixed, too.

- Fix #3348, by adding passing tests.

- Fix #3529: If a string starts with an interpolation, an empty string is no
  longer emitted before the interpolation (unless it is needed to coerce the
  interpolation into a string).

- Block comments cannot contain `*/`. Now the error message also shows exactly
  where the offending `*/`. This improvement might seem unrelated, but I had to
  touch that code anyway to refactor string and regex related code, and the
  change was very trivial. Moreover, it's consistent with the next two points.

- Regexes cannot start with `*`. Now the error message also shows exactly where
  the offending `*` is. (It might actually not be exatly at the start in
  heregexes.) It is a very minor improvement, but it was trivial to add.

- Octal escapes in strings are forbidden in CoffeeScript (just like in
  JavaScript strict mode). However, this used to be the case only for regular
  strings. Now they are also forbidden in heredocs. Moreover, the errors now
  point at the offending octal escape.

- Invalid regex flags are no longer allowed. This includes repeated modifiers
  and unknown ones. Moreover, invalid modifiers do not stop a heregex from
  being matched, which results in better error messages.

- Fix #3621: `///a#{1}///` compiles to `RegExp("a" + 1)`. So does
  `RegExp("a#{1}")`. Still, those two code snippets used to generate different
  tokens, which is a bit weird, but more importantly causes problems for
  coffeelint (see clutchski/coffeelint#340). This required lots of tests in
  test/location.coffee to be updated. Note that some updates to those tests are
  unrelated to this point; some have been updated to be more consistent (I
  discovered this because the refactored code happened to be seemingly more
  correct).

- Regular regex literals used to erraneously allow newlines to be escaped,
  causing invalid JavaScript output. This has been fixed.

- Heregexes may now be completely empty (`//////`), instead of erroring out with
  a confusing message.

- Fix #2388: Heredocs and heregexes used to be lexed simply, which meant that
  you couldn't nest a heredoc within a heredoc (double-quoted, that is) or a
  heregex inside a heregex.

- Fix #2321: If you used division inside interpolation and then a slash later in
  the string containing that interpolation, the division slash and the latter
  slash was erraneously matched as a regex. This has been fixed.

- Indentation inside interpolations in heredocs no longer affect how much
  indentation is removed from each line of the heredoc (which is more
  intuitive).

- Whitespace is now correctly trimmed from the start and end of strings in a few
  edge cases.

- Last but not least, the lexing of interpolated strings now seems to be more
  efficient. For a regular double-quoted string, we used to use a custom
  function to find the end of it (taking interpolations and interpolations
  within interpolations etc. into account). Then we used to re-find the
  interpolations and recursively lex their contents. In effect, the same string
  was processed twice, or even more in the case of deeper nesting of
  interpolations. Now the same string is processed just once.

- Code duplication between regular strings, heredocs, regular regexes and
  heregexes has been reduced.

- The above two points should result in more easily read code, too.
2015-01-04 07:47:09 +01:00

494 lines
12 KiB
CoffeeScript

testScript = '''
if true
x = 6
console.log "A console #{x + 7} log"
foo = "bar"
z = /// ^ (a#{foo}) ///
x = () ->
try
console.log "foo"
catch err
# Rewriter will generate explicit indentation here.
return null
'''
test "Verify location of generated tokens", ->
tokens = CoffeeScript.tokens "a = 79"
eq tokens.length, 4
aToken = tokens[0]
eq aToken[2].first_line, 0
eq aToken[2].first_column, 0
eq aToken[2].last_line, 0
eq aToken[2].last_column, 0
equalsToken = tokens[1]
eq equalsToken[2].first_line, 0
eq equalsToken[2].first_column, 2
eq equalsToken[2].last_line, 0
eq equalsToken[2].last_column, 2
numberToken = tokens[2]
eq numberToken[2].first_line, 0
eq numberToken[2].first_column, 4
eq numberToken[2].last_line, 0
eq numberToken[2].last_column, 5
test "Verify location of generated tokens (with indented first line)", ->
tokens = CoffeeScript.tokens " a = 83"
eq tokens.length, 4
[aToken, equalsToken, numberToken] = tokens
eq aToken[2].first_line, 0
eq aToken[2].first_column, 2
eq aToken[2].last_line, 0
eq aToken[2].last_column, 2
eq equalsToken[2].first_line, 0
eq equalsToken[2].first_column, 4
eq equalsToken[2].last_line, 0
eq equalsToken[2].last_column, 4
eq numberToken[2].first_line, 0
eq numberToken[2].first_column, 6
eq numberToken[2].last_line, 0
eq numberToken[2].last_column, 7
test 'Verify locations in string interpolation (in "string")', ->
tokens = CoffeeScript.tokens '"a#{b}c"'
eq tokens.length, 8
[openParen, a, firstPlus, b, secondPlus, c, closeParen] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 1
eq a[2].last_line, 0
eq a[2].last_column, 1
eq b[2].first_line, 0
eq b[2].first_column, 4
eq b[2].last_line, 0
eq b[2].last_column, 4
eq c[2].first_line, 0
eq c[2].first_column, 6
eq c[2].last_line, 0
eq c[2].last_column, 6
test 'Verify locations in string interpolation (in "string", multiple interpolation)', ->
tokens = CoffeeScript.tokens '"#{a}b#{c}"'
eq tokens.length, 8
[{}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 3
eq a[2].last_line, 0
eq a[2].last_column, 3
eq b[2].first_line, 0
eq b[2].first_column, 5
eq b[2].last_line, 0
eq b[2].last_column, 5
eq c[2].first_line, 0
eq c[2].first_column, 8
eq c[2].last_line, 0
eq c[2].last_column, 8
test 'Verify locations in string interpolation (in "string", multiple interpolation and line breaks)', ->
tokens = CoffeeScript.tokens '"#{a}\nb\n#{c}"'
eq tokens.length, 8
[{}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 3
eq a[2].last_line, 0
eq a[2].last_column, 3
eq b[2].first_line, 0
eq b[2].first_column, 5
eq b[2].last_line, 1
eq b[2].last_column, 1
eq c[2].first_line, 2
eq c[2].first_column, 2
eq c[2].last_line, 2
eq c[2].last_column, 2
test 'Verify locations in string interpolation (in "string", multiple interpolation and starting with line breaks)', ->
tokens = CoffeeScript.tokens '"\n#{a}\nb\n#{c}"'
eq tokens.length, 8
[{}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 1
eq a[2].first_column, 2
eq a[2].last_line, 1
eq a[2].last_column, 2
eq b[2].first_line, 1
eq b[2].first_column, 4
eq b[2].last_line, 2
eq b[2].last_column, 1
eq c[2].first_line, 3
eq c[2].first_column, 2
eq c[2].last_line, 3
eq c[2].last_column, 2
test 'Verify locations in string interpolation (in "string", multiple interpolation and starting with line breaks)', ->
tokens = CoffeeScript.tokens '"\n\n#{a}\n\nb\n\n#{c}"'
eq tokens.length, 8
[{}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 2
eq a[2].first_column, 2
eq a[2].last_line, 2
eq a[2].last_column, 2
eq b[2].first_line, 2
eq b[2].first_column, 4
eq b[2].last_line, 5
eq b[2].last_column, 0
eq c[2].first_line, 6
eq c[2].first_column, 2
eq c[2].last_line, 6
eq c[2].last_column, 2
test 'Verify locations in string interpolation (in "string", multiple interpolation and starting with line breaks)', ->
tokens = CoffeeScript.tokens '"\n\n\n#{a}\n\n\nb\n\n\n#{c}"'
eq tokens.length, 8
[{}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 3
eq a[2].first_column, 2
eq a[2].last_line, 3
eq a[2].last_column, 2
eq b[2].first_line, 3
eq b[2].first_column, 4
eq b[2].last_line, 8
eq b[2].last_column, 0
eq c[2].first_line, 9
eq c[2].first_column, 2
eq c[2].last_line, 9
eq c[2].last_column, 2
test 'Verify locations in string interpolation (in """string""", line breaks)', ->
tokens = CoffeeScript.tokens '"""a\n#{b}\nc"""'
eq tokens.length, 8
[{}, a, {}, b, {}, c, {}, {}] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 3
eq a[2].last_line, 0
eq a[2].last_column, 4
eq b[2].first_line, 1
eq b[2].first_column, 2
eq b[2].last_line, 1
eq b[2].last_column, 2
eq c[2].first_line, 1
eq c[2].first_column, 4
eq c[2].last_line, 2
eq c[2].last_column, 0
test 'Verify locations in string interpolation (in """string""", starting with a line break)', ->
tokens = CoffeeScript.tokens '"""\n#{b}\nc"""'
eq tokens.length, 6
[{}, b, {}, c] = tokens
eq b[2].first_line, 1
eq b[2].first_column, 2
eq b[2].last_line, 1
eq b[2].last_column, 2
eq c[2].first_line, 1
eq c[2].first_column, 4
eq c[2].last_line, 2
eq c[2].last_column, 0
test 'Verify locations in string interpolation (in """string""", starting with line breaks)', ->
tokens = CoffeeScript.tokens '"""\n\n#{b}\nc"""'
eq tokens.length, 8
[{}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 3
eq a[2].last_line, 1
eq a[2].last_column, 0
eq b[2].first_line, 2
eq b[2].first_column, 2
eq b[2].last_line, 2
eq b[2].last_column, 2
eq c[2].first_line, 2
eq c[2].first_column, 4
eq c[2].last_line, 3
eq c[2].last_column, 0
test 'Verify locations in string interpolation (in """string""", multiple interpolation)', ->
tokens = CoffeeScript.tokens '"""#{a}\nb\n#{c}"""'
eq tokens.length, 8
[{}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 5
eq a[2].last_line, 0
eq a[2].last_column, 5
eq b[2].first_line, 0
eq b[2].first_column, 7
eq b[2].last_line, 1
eq b[2].last_column, 1
eq c[2].first_line, 2
eq c[2].first_column, 2
eq c[2].last_line, 2
eq c[2].last_column, 2
test 'Verify locations in string interpolation (in """string""", multiple interpolation, and starting with line breaks)', ->
tokens = CoffeeScript.tokens '"""\n\n#{a}\n\nb\n\n#{c}"""'
eq tokens.length, 10
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 2
eq a[2].first_column, 2
eq a[2].last_line, 2
eq a[2].last_column, 2
eq b[2].first_line, 2
eq b[2].first_column, 4
eq b[2].last_line, 5
eq b[2].last_column, 0
eq c[2].first_line, 6
eq c[2].first_column, 2
eq c[2].last_line, 6
eq c[2].last_column, 2
test 'Verify locations in string interpolation (in """string""", multiple interpolation, and starting with line breaks)', ->
tokens = CoffeeScript.tokens '"""\n\n\n#{a}\n\n\nb\n\n\n#{c}"""'
eq tokens.length, 10
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 3
eq a[2].first_column, 2
eq a[2].last_line, 3
eq a[2].last_column, 2
eq b[2].first_line, 3
eq b[2].first_column, 4
eq b[2].last_line, 8
eq b[2].last_column, 0
eq c[2].first_line, 9
eq c[2].first_column, 2
eq c[2].last_line, 9
eq c[2].last_column, 2
test 'Verify locations in heregex interpolation (in ///regex///, multiple interpolation)', ->
tokens = CoffeeScript.tokens '///#{a}b#{c}///'
eq tokens.length, 11
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 5
eq a[2].last_line, 0
eq a[2].last_column, 5
eq b[2].first_line, 0
eq b[2].first_column, 7
eq b[2].last_line, 0
eq b[2].last_column, 7
eq c[2].first_line, 0
eq c[2].first_column, 10
eq c[2].last_line, 0
eq c[2].last_column, 10
test 'Verify locations in heregex interpolation (in ///regex///, multiple interpolation)', ->
tokens = CoffeeScript.tokens '///a#{b}c///'
eq tokens.length, 11
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 3
eq a[2].last_line, 0
eq a[2].last_column, 3
eq b[2].first_line, 0
eq b[2].first_column, 6
eq b[2].last_line, 0
eq b[2].last_column, 6
eq c[2].first_line, 0
eq c[2].first_column, 8
eq c[2].last_line, 0
eq c[2].last_column, 8
test 'Verify locations in heregex interpolation (in ///regex///, multiple interpolation and line breaks)', ->
tokens = CoffeeScript.tokens '///#{a}\nb\n#{c}///'
eq tokens.length, 11
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 5
eq a[2].last_line, 0
eq a[2].last_column, 5
eq b[2].first_line, 0
eq b[2].first_column, 7
eq b[2].last_line, 1
eq b[2].last_column, 1
eq c[2].first_line, 2
eq c[2].first_column, 2
eq c[2].last_line, 2
eq c[2].last_column, 2
test 'Verify locations in heregex interpolation (in ///regex///, multiple interpolation and line breaks)', ->
tokens = CoffeeScript.tokens '///#{a}\n\n\nb\n\n\n#{c}///'
eq tokens.length, 11
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 5
eq a[2].last_line, 0
eq a[2].last_column, 5
eq b[2].first_line, 0
eq b[2].first_column, 7
eq b[2].last_line, 5
eq b[2].last_column, 0
eq c[2].first_line, 6
eq c[2].first_column, 2
eq c[2].last_line, 6
eq c[2].last_column, 2
test 'Verify locations in heregex interpolation (in ///regex///, multiple interpolation and line breaks)', ->
tokens = CoffeeScript.tokens '///a\n\n\n#{b}\n\n\nc///'
eq tokens.length, 11
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 3
eq a[2].last_line, 2
eq a[2].last_column, 0
eq b[2].first_line, 3
eq b[2].first_column, 2
eq b[2].last_line, 3
eq b[2].last_column, 2
eq c[2].first_line, 3
eq c[2].first_column, 4
eq c[2].last_line, 6
eq c[2].last_column, 0
test 'Verify locations in heregex interpolation (in ///regex///, multiple interpolation and line breaks and starting with linebreak)', ->
tokens = CoffeeScript.tokens '///\n#{a}\nb\n#{c}///'
eq tokens.length, 11
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 1
eq a[2].first_column, 2
eq a[2].last_line, 1
eq a[2].last_column, 2
eq b[2].first_line, 1
eq b[2].first_column, 4
eq b[2].last_line, 2
eq b[2].last_column, 1
eq c[2].first_line, 3
eq c[2].first_column, 2
eq c[2].last_line, 3
eq c[2].last_column, 2
test 'Verify locations in heregex interpolation (in ///regex///, multiple interpolation and line breaks and starting with linebreak)', ->
tokens = CoffeeScript.tokens '///\n\n\n#{a}\n\n\nb\n\n\n#{c}///'
eq tokens.length, 11
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 3
eq a[2].first_column, 2
eq a[2].last_line, 3
eq a[2].last_column, 2
eq b[2].first_line, 3
eq b[2].first_column, 4
eq b[2].last_line, 8
eq b[2].last_column, 0
eq c[2].first_line, 9
eq c[2].first_column, 2
eq c[2].last_line, 9
eq c[2].last_column, 2
test 'Verify locations in heregex interpolation (in ///regex///, multiple interpolation and line breaks and starting with linebreak)', ->
tokens = CoffeeScript.tokens '///\n\n\na\n\n\n#{b}\n\n\nc///'
eq tokens.length, 11
[{}, {}, {}, a, {}, b, {}, c] = tokens
eq a[2].first_line, 0
eq a[2].first_column, 3
eq a[2].last_line, 5
eq a[2].last_column, 0
eq b[2].first_line, 6
eq b[2].first_column, 2
eq b[2].last_line, 6
eq b[2].last_column, 2
eq c[2].first_line, 6
eq c[2].first_column, 4
eq c[2].last_line, 9
eq c[2].last_column, 0
test "#3621: Multiline regex and manual `Regex` call with interpolation should
result in the same tokens", ->
tokensA = CoffeeScript.tokens 'RegExp(".*#{a}[0-9]")'
tokensB = CoffeeScript.tokens '///.*#{a}[0-9]///'
eq tokensA.length, tokensB.length
for i in [0...tokensA.length] by 1
tokenA = tokensA[i]
tokenB = tokensB[i]
eq tokenA[0], tokenB[0]
eq tokenA[1], tokenB[1]
eq tokenA.origin?[1], tokenB.origin?[1]
eq tokenA.stringEnd, tokenB.stringEnd
test "Verify all tokens get a location", ->
doesNotThrow ->
tokens = CoffeeScript.tokens testScript
for token in tokens
ok !!token[2]