diff --git a/LICENSE b/LICENSE new file mode 100644 --- /dev/null +++ b/LICENSE @@ -0,0 +1,30 @@ +Copyright (c)2011, Jason Dagit + +All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following + disclaimer in the documentation and/or other materials provided + with the distribution. + + * Neither the name of Jason Dagit nor the names of other + contributors may be used to endorse or promote products derived + from this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/Setup.hs b/Setup.hs new file mode 100644 --- /dev/null +++ b/Setup.hs @@ -0,0 +1,2 @@ +import Distribution.Simple +main = defaultMain diff --git a/Text/Encoding/Z.hs b/Text/Encoding/Z.hs new file mode 100644 --- /dev/null +++ b/Text/Encoding/Z.hs @@ -0,0 +1,212 @@ +{- | The Z-encoding + +This is the main name-encoding and decoding function. It encodes any +string into a string that is acceptable as a C name. This is done +right before we emit a symbol name into the compiled C or asm code. +Z-encoding of strings is cached in the FastString interface, so we +never encode the same string more than once. + +The basic encoding scheme is this. + + * Tuples (,,,) are coded as Z3T + + * Alphabetic characters (upper and lower) and digits + all translate to themselves; + except 'Z', which translates to 'ZZ' + and 'z', which translates to 'zz' + We need both so that we can preserve the variable/tycon distinction + + * Most other printable characters translate to 'zx' or 'Zx' for some + alphabetic character x + + * The others translate as 'znnnU' where 'nnn' is the decimal number + of the character + +@ + Before After + -------------------------- + Trak Trak + foo_wib foozuwib + \> zg + \>1 zg1 + foo\# foozh + foo\#\# foozhzh + foo\#\#1 foozhzh1 + fooZ fooZZ + :+ ZCzp + () Z0T 0-tuple + (,,,,) Z5T 5-tuple + (\# \#) Z1H unboxed 1-tuple (note the space) + (\#,,,,\#) Z5H unboxed 5-tuple + (NB: There is no Z1T nor Z0H.) +@ +-} +module Text.Encoding.Z ( + zEncodeString, + zDecodeString, + UserString, + EncodedString +) where + +import Data.Char +import Numeric + +type UserString = String -- As the user typed it +type EncodedString = String -- Encoded form + + +zEncodeString :: UserString -> EncodedString +zEncodeString cs = case maybe_tuple cs of + Just n -> n -- Tuples go to Z2T etc + Nothing -> go cs + where + go [] = [] + go (c:cs) = encode_digit_ch c ++ go' cs + go' [] = [] + go' (c:cs) = encode_ch c ++ go' cs + +unencodedChar :: Char -> Bool -- True for chars that don't need encoding +unencodedChar 'Z' = False +unencodedChar 'z' = False +unencodedChar c = c >= 'a' && c <= 'z' + || c >= 'A' && c <= 'Z' + || c >= '0' && c <= '9' + +-- If a digit is at the start of a symbol then we need to encode it. +-- Otherwise package names like 9pH-0.1 give linker errors. +encode_digit_ch :: Char -> EncodedString +encode_digit_ch c | c >= '0' && c <= '9' = encode_as_unicode_char c +encode_digit_ch c | otherwise = encode_ch c + +encode_ch :: Char -> EncodedString +encode_ch c | unencodedChar c = [c] -- Common case first + +-- Constructors +encode_ch '(' = "ZL" -- Needed for things like (,), and (->) +encode_ch ')' = "ZR" -- For symmetry with ( +encode_ch '[' = "ZM" +encode_ch ']' = "ZN" +encode_ch ':' = "ZC" +encode_ch 'Z' = "ZZ" + +-- Variables +encode_ch 'z' = "zz" +encode_ch '&' = "za" +encode_ch '|' = "zb" +encode_ch '^' = "zc" +encode_ch '$' = "zd" +encode_ch '=' = "ze" +encode_ch '>' = "zg" +encode_ch '#' = "zh" +encode_ch '.' = "zi" +encode_ch '<' = "zl" +encode_ch '-' = "zm" +encode_ch '!' = "zn" +encode_ch '+' = "zp" +encode_ch '\'' = "zq" +encode_ch '\\' = "zr" +encode_ch '/' = "zs" +encode_ch '*' = "zt" +encode_ch '_' = "zu" +encode_ch '%' = "zv" +encode_ch c = encode_as_unicode_char c + +encode_as_unicode_char :: Char -> EncodedString +encode_as_unicode_char c = 'z' : if isDigit (head hex_str) then hex_str + else '0':hex_str + where hex_str = showHex (ord c) "U" + -- ToDo: we could improve the encoding here in various ways. + -- eg. strings of unicode characters come out as 'z1234Uz5678U', we + -- could remove the 'U' in the middle (the 'z' works as a separator). + +zDecodeString :: EncodedString -> UserString +zDecodeString [] = [] +zDecodeString ('Z' : d : rest) + | isDigit d = decode_tuple d rest + | otherwise = decode_upper d : zDecodeString rest +zDecodeString ('z' : d : rest) + | isDigit d = decode_num_esc d rest + | otherwise = decode_lower d : zDecodeString rest +zDecodeString (c : rest) = c : zDecodeString rest + +decode_upper, decode_lower :: Char -> Char + +decode_upper 'L' = '(' +decode_upper 'R' = ')' +decode_upper 'M' = '[' +decode_upper 'N' = ']' +decode_upper 'C' = ':' +decode_upper 'Z' = 'Z' +decode_upper ch = {-pprTrace "decode_upper" (char ch)-} ch + +decode_lower 'z' = 'z' +decode_lower 'a' = '&' +decode_lower 'b' = '|' +decode_lower 'c' = '^' +decode_lower 'd' = '$' +decode_lower 'e' = '=' +decode_lower 'g' = '>' +decode_lower 'h' = '#' +decode_lower 'i' = '.' +decode_lower 'l' = '<' +decode_lower 'm' = '-' +decode_lower 'n' = '!' +decode_lower 'p' = '+' +decode_lower 'q' = '\'' +decode_lower 'r' = '\\' +decode_lower 's' = '/' +decode_lower 't' = '*' +decode_lower 'u' = '_' +decode_lower 'v' = '%' +decode_lower ch = {-pprTrace "decode_lower" (char ch)-} ch + +-- Characters not having a specific code are coded as z224U (in hex) +decode_num_esc :: Char -> EncodedString -> UserString +decode_num_esc d rest + = go (digitToInt d) rest + where + go n (c : rest) | isHexDigit c = go (16*n + digitToInt c) rest + go n ('U' : rest) = chr n : zDecodeString rest + go n other = error ("decode_num_esc: " ++ show n ++ ' ':other) + +decode_tuple :: Char -> EncodedString -> UserString +decode_tuple d rest + = go (digitToInt d) rest + where + -- NB. recurse back to zDecodeString after decoding the tuple, because + -- the tuple might be embedded in a longer name. + go n (c : rest) | isDigit c = go (10*n + digitToInt c) rest + go 0 ('T':rest) = "()" ++ zDecodeString rest + go n ('T':rest) = '(' : replicate (n-1) ',' ++ ")" ++ zDecodeString rest + go 1 ('H':rest) = "(# #)" ++ zDecodeString rest + go n ('H':rest) = '(' : '#' : replicate (n-1) ',' ++ "#)" ++ zDecodeString rest + go n other = error ("decode_tuple: " ++ show n ++ ' ':other) + +{- +Tuples are encoded as + Z3T or Z3H +for 3-tuples or unboxed 3-tuples respectively. No other encoding starts + Z + +* "(# #)" is the tycon for an unboxed 1-tuple (not 0-tuple) + There are no unboxed 0-tuples. + +* "()" is the tycon for a boxed 0-tuple. + There are no boxed 1-tuples. +-} + +maybe_tuple :: UserString -> Maybe EncodedString + +maybe_tuple "(# #)" = Just("Z1H") +maybe_tuple ('(' : '#' : cs) = case count_commas (0::Int) cs of + (n, '#' : ')' : _) -> Just ('Z' : shows (n+1) "H") + _ -> Nothing +maybe_tuple "()" = Just("Z0T") +maybe_tuple ('(' : cs) = case count_commas (0::Int) cs of + (n, ')' : _) -> Just ('Z' : shows (n+1) "T") + _ -> Nothing +maybe_tuple _ = Nothing + +count_commas :: Int -> String -> (Int, String) +count_commas n (',' : cs) = count_commas (n+1) cs +count_commas n cs = (n,cs) diff --git a/zenc.cabal b/zenc.cabal new file mode 100644 --- /dev/null +++ b/zenc.cabal @@ -0,0 +1,33 @@ +Name: zenc +Version: 0.1.1 +Synopsis: GHC style name Z-encoding and Z-decoding +Description: Implements GHC's name mangling. This code was taken + directly from the GHC source. +License: BSD3 +License-file: LICENSE +Author: GHC Team, Jason Dagit +Maintainer: dagitj@gmail.com +Copyright: GHC HQ +Category: Text +Build-type: Simple +Cabal-version: >=1.6 + + +Library + -- Modules exported by the library. + Exposed-modules: Text.Encoding.Z + + -- Packages needed in order to build this package. + Build-depends: base >= 3 && <= 5 + GHC-options: -O2 + + -- Modules not exported by this package. + -- Other-modules: + + -- Extra tools (e.g. alex, hsc2hs, ...) needed to build the source. + -- Build-tools: + +source-repository this + type: git + location: git://github.com/dagit/zenc.git + tag: 0.1.0