diff --git a/ChangeLog.md b/ChangeLog.md --- a/ChangeLog.md +++ b/ChangeLog.md @@ -1,5 +1,12 @@ # Revision history for toml-parser +## 2.0.2.0 + +* Update for TOML 1.1.0 + - Add \e and \x escapes + - Allow omitting seconds in times + - Allow newlines and trailing commas in inline tables + ## 2.0.1.2 * Reject inputs with out-of-bounds time zone offsets in accordance diff --git a/README.lhs b/README.lhs --- a/README.lhs +++ b/README.lhs @@ -1,6 +1,6 @@ # TOML Parser -This package implements a validating parser for [TOML 1.0.0](https://toml.io/en/v1.0.0). +This package implements a validating parser for [TOML 1.1.0](https://toml.io/en/v1.1.0). This package uses an [alex](https://haskell-alex.readthedocs.io/en/latest/)-generated lexer and [happy](https://haskell-happy.readthedocs.io/en/latest/)-generated parser. diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # TOML Parser -This package implements a validating parser for [TOML 1.0.0](https://toml.io/en/v1.0.0). +This package implements a validating parser for [TOML 1.1.0](https://toml.io/en/v1.1.0). This package uses an [alex](https://haskell-alex.readthedocs.io/en/latest/)-generated lexer and [happy](https://haskell-happy.readthedocs.io/en/latest/)-generated parser. diff --git a/src/Toml.hs b/src/Toml.hs --- a/src/Toml.hs +++ b/src/Toml.hs @@ -10,7 +10,7 @@ It enables parsing, printing, and conversion into and out of application-specific representations. -This parser implements TOML 1.0.0 +This parser implements TOML 1.1.0 as carefully as possible. Use "Toml.Schema" to implement functions mapping between TOML diff --git a/src/Toml/Pretty.hs b/src/Toml/Pretty.hs --- a/src/Toml/Pretty.hs +++ b/src/Toml/Pretty.hs @@ -94,12 +94,14 @@ '"' : xs -> '\\' : '"' : go xs '\\' : xs -> '\\' : '\\' : go xs '\b' : xs -> '\\' : 'b' : go xs + '\ESC':xs -> '\\' : 'e' : go xs '\f' : xs -> '\\' : 'f' : go xs '\n' : xs -> '\\' : 'n' : go xs '\r' : xs -> '\\' : 'r' : go xs '\t' : xs -> '\\' : 't' : go xs x : xs | isPrint x -> x : go xs + | x <= '\xff' -> printf "\\x%02X%s" (ord x) (go xs) | x <= '\xffff' -> printf "\\u%04X%s" (ord x) (go xs) | otherwise -> printf "\\U%08X%s" (ord x) (go xs) @@ -112,6 +114,7 @@ '"' : '"' : '"' : xs -> "\"\"\\\"" ++ go xs '\\' : xs -> '\\' : '\\' : go xs '\b' : xs -> '\\' : 'b' : go xs + '\ESC':xs -> '\\' : 'e' : go xs '\f' : xs -> '\\' : 'f' : go xs '\t' : xs -> '\\' : 't' : go xs '\n' : xs -> '\n' : go xs @@ -119,6 +122,7 @@ '\r' : xs -> '\\' : 'r' : go xs x : xs | isPrint x -> x : go xs + | x <= '\xff' -> printf "\\x%02X%s" (ord x) (go xs) | x <= '\xffff' -> printf "\\u%04X%s" (ord x) (go xs) | otherwise -> printf "\\U%08X%s" (ord x) (go xs) diff --git a/src/Toml/Syntax/Lexer.x b/src/Toml/Syntax/Lexer.x --- a/src/Toml/Syntax/Lexer.x +++ b/src/Toml/Syntax/Lexer.x @@ -63,8 +63,7 @@ $literal_char = [\x09 \x20-\x26 \x28-\x7E $non_ascii] -$mll_char = [\x09 \x20-\x26 \x28-\x7E $non_ascii] -@mll_content = $mll_char | @newline +@mll_content = $literal_char | @newline @mlb_escaped_nl = \\ @ws @newline ($wschar | @newline)* $unescaped = [$wschar \x21 \x23-\x5B \x5D-\x7E $non_ascii] @@ -82,7 +81,7 @@ @time_numoffset = [\+\-] @offset_hour ":" @offset_minute @time_offset = [Zz] | @time_numoffset -@partial_time = @time_hour ":" @time_minute ":" @time_second @time_secfrac? +@partial_time = @time_hour ":" @time_minute (":" @time_second @time_secfrac?)? @full_date = @date_fullyear "-" @date_month "-" @date_mday @full_time = @partial_time @time_offset @@ -164,15 +163,18 @@ } { - \\ U $hexdig{8} { unicodeEscape } - \\ U { failure "\\U requires exactly 8 hex digits"} + \\ x $hexdig{2} { unicodeEscape } + \\ x { failure "\\x requires exactly 2 hex digits"} \\ u $hexdig{4} { unicodeEscape } \\ u { failure "\\u requires exactly 4 hex digits"} + \\ U $hexdig{8} { unicodeEscape } + \\ U { failure "\\U requires exactly 8 hex digits"} \\ n { strFrag . (Text.singleton '\n' <$) } \\ t { strFrag . (Text.singleton '\t' <$) } \\ r { strFrag . (Text.singleton '\r' <$) } \\ f { strFrag . (Text.singleton '\f' <$) } \\ b { strFrag . (Text.singleton '\b' <$) } + \\ e { strFrag . (Text.singleton '\ESC' <$) } \\ \\ { strFrag . (Text.singleton '\\' <$) } \\ \" { strFrag . (Text.singleton '\"' <$) } \\ . { failure "unknown escape sequence" } diff --git a/src/Toml/Syntax/Parser.y b/src/Toml/Syntax/Parser.y --- a/src/Toml/Syntax/Parser.y +++ b/src/Toml/Syntax/Parser.y @@ -99,8 +99,17 @@ | inlinetable { locVal ValTable $1 } inlinetable :: { Located [(Key Position, Val Position)] } - : lhs '{' sepBy(keyval, ',') pop '}' - { Located $2 $3 } + : lhs '{' inlinetablekeyvals newlines pop '}' + { Located $2 (reverse $3) } + | lhs '{' inlinetablekeyvals newlines ',' newlines pop '}' + { Located $2 (reverse $3) } + | lhs '{' newlines pop '}' + { Located $2 [] } + +inlinetablekeyvals :: { [(Key Position, Val Position)] } + : newlines keyval { [$2] } + | inlinetablekeyvals newlines ',' newlines keyval + { $5 : $1 } array :: { Located [Val Position] } : rhs '[' newlines pop ']' diff --git a/src/Toml/Syntax/Token.hs b/src/Toml/Syntax/Token.hs --- a/src/Toml/Syntax/Token.hs +++ b/src/Toml/Syntax/Token.hs @@ -108,16 +108,26 @@ -- | Format strings for local time lexemes. localTimePatterns :: [String] -localTimePatterns = ["%H:%M:%S%Q"] +localTimePatterns = + ["%H:%M:%S%Q", + "%H:%M"] -- | Format strings for local datetime lexemes. localDateTimePatterns :: [String] localDateTimePatterns = ["%Y-%m-%dT%H:%M:%S%Q", - "%Y-%m-%d %H:%M:%S%Q"] + "%Y-%m-%d %H:%M:%S%Q", + "%Y-%m-%dT%H:%M", + "%Y-%m-%d %H:%M"] -- | Format strings for offset datetime lexemes. offsetDateTimePatterns :: [String] offsetDateTimePatterns = - ["%Y-%m-%dT%H:%M:%S%Q%Ez","%Y-%m-%dT%H:%M:%S%QZ", - "%Y-%m-%d %H:%M:%S%Q%Ez","%Y-%m-%d %H:%M:%S%QZ"] + ["%Y-%m-%dT%H:%M:%S%Q%Ez", + "%Y-%m-%dT%H:%M:%S%QZ", + "%Y-%m-%d %H:%M:%S%Q%Ez", + "%Y-%m-%d %H:%M:%S%QZ", + "%Y-%m-%dT%H:%M%Ez", + "%Y-%m-%dT%H:%MZ", + "%Y-%m-%d %H:%M%Ez", + "%Y-%m-%d %H:%MZ"] diff --git a/test/PrettySpec.hs b/test/PrettySpec.hs --- a/test/PrettySpec.hs +++ b/test/PrettySpec.hs @@ -61,9 +61,9 @@ y = 4|] it "renders escapes in strings" $ - fmap tomlString (parse_ "a=\"\\\\\\b\\t\\r\\n\\f\\\"\\u007f\\U0001000c\"") + fmap tomlString (parse_ "a=\"\\\\\\b\\t\\r\\n\\f\\e\\\"\\u007f\\U0001000c\"") `shouldBe` Right [quoteStr| - a = "\\\b\t\r\n\f\"\u007F\U0001000C"|] + a = "\\\b\t\r\n\f\e\"\x7F\U0001000C"|] it "renders multiline strings" $ fmap tomlString (parse_ [quoteStr| diff --git a/toml-parser.cabal b/toml-parser.cabal --- a/toml-parser.cabal +++ b/toml-parser.cabal @@ -1,10 +1,10 @@ cabal-version: 3.0 name: toml-parser -version: 2.0.1.2 -synopsis: TOML 1.0.0 parser +version: 2.0.2.0 +synopsis: TOML 1.1.0 parser description: TOML parser using generated lexers and parsers with - careful attention to the TOML 1.0.0 semantics for + careful attention to the TOML 1.1.0 semantics for defining tables. license: ISC license-file: LICENSE @@ -13,7 +13,7 @@ copyright: 2023 Eric Mertens category: Text build-type: Simple -tested-with: GHC == {8.10.7, 9.0.2, 9.2.8, 9.4.8, 9.6.6, 9.8.2, 9.10.1, 9.12.2} +tested-with: GHC == {8.10.7, 9.0.2, 9.2.8, 9.4.8, 9.6.7, 9.8.4, 9.10.3, 9.12.2} extra-doc-files: ChangeLog.md @@ -75,7 +75,7 @@ containers ^>= {0.5, 0.6, 0.7, 0.8}, prettyprinter ^>= 1.7, text >= 0.2 && < 3, - time ^>= {1.9, 1.10, 1.11, 1.12, 1.14}, + time ^>= {1.9, 1.10, 1.11, 1.12, 1.14, 1.15}, transformers ^>= {0.5, 0.6}, build-tool-depends: alex:alex >= 3.2,