diff --git a/ChangeLog b/ChangeLog new file mode 100644 --- /dev/null +++ b/ChangeLog @@ -0,0 +1,17 @@ +0.0.3.0 + [AJR] Initial public release. + +0.0.4.0 + [AJR] Fixed various bugs. + +0.0.5.0 + [AJR] Added testing framework. + [AJR] Added /begin/:/end/ expressions. + +0.0.6.0 + [AJR] Fixed a sign problem in getIndex. + [AJR] Fixed issues in the manpage. + + + + diff --git a/only.1 b/only.1 --- a/only.1 +++ b/only.1 @@ -143,7 +143,7 @@ expr = do optional numeric c <- punct ; regex ; c - (try c ; regex ; c ; optional num + (try c ; regex ; c ; optional num | optional numeric) | numeric | regex @@ -181,7 +181,7 @@ .I M are known as .I relative indices. -Absolute indices will take the list of matches (the list of tokens that were matched by the regular expression), and apply use the numbers in M as the indices of this list. This gives you the ability to select the first match (1) or the last match (-1). If you use negative numbers, then it will count from the end of file going backwards, so (-2) would be the second to last match. Relative indices will take the list of matches, the original list of tokens, and for each match, it forms a virtual list where 0 refers to the match's index in the list of tokens. This allows one to emulate +Absolute indices will take the list of matches (the list of tokens that were matched by the regular expression), and apply use the numbers in N as the indices of this list. This gives you the ability to select the first match (1) or the last match (-1). If you use negative numbers, then it will count from the end of file going backwards, so (-2) would be the second to last match. Relative indices will take the list of matches, the original list of tokens, and for each match, it forms a virtual list where 0 refers to the match's index in the list of tokens. This allows one to emulate .B grep's \-A (after) and \-B (before) options. .P diff --git a/only.cabal b/only.cabal --- a/only.cabal +++ b/only.cabal @@ -1,5 +1,5 @@ Cabal-version: >= 1.2.0.0 -version: 0.0.5.0 +version: 0.0.6.0 name: only license: GPL @@ -16,16 +16,21 @@ you search with 'only -l patt' but you can select the n-th match with '-l n\/patt\/' and the next 3 lines with '-l \/patt\/0:3'. extra-source-files: + ChangeLog AUTHORS LICENSE README only.1 tests/e-both.txt + tests/e-semi.txt tests/i-all.sh tests/Makefile tests/README + tests/t-cut-2.sh + tests/t-cut-semi.sh tests/t-eq-abs.sh tests/t-eq-nil.sh + tests/t-eq-no-debug.sh tests/t-eq-regex-char.sh tests/t-eq-regex-zero.sh tests/t-eq-regex.sh @@ -33,6 +38,8 @@ tests/t-grep-before.sh tests/t-grep-dot.sh tests/t-grep-to.sh + tests/t-head.sh + tests/t-tail.sh executable only main-is: only.hs diff --git a/only.hs b/only.hs --- a/only.hs +++ b/only.hs @@ -7,6 +7,7 @@ import Control.Monad (when, unless) import Data.IORef import Data.Maybe +import Data.List import System.Console.GetOpt import System.Environment (getArgs) import System.Exit @@ -20,7 +21,7 @@ progName = "only" -- usage stuff -version = "only (GNU Only) 0.0.5.0\n" +version = "only (GNU Only) 0.0.6.0\n" header = unlines [ version, @@ -69,6 +70,7 @@ -- , Option ['b'] ["bits"] (ReqArg (\x -> ('b', x)) "EXPR") "Bit expression" -- , Option ['B'] ["bytes"] (ReqArg (\x -> ('B', x)) "EXPR") "Byte expression" -- , Option ['c'] ["chars"] (ReqArg (\x -> ('c', x)) "EXPR") "Character expression" + , Option ['W'] ["wordsep"] (ReqArg (\x -> ('W', x)) "EXPR") "Word seperator" , Option ['w'] ["words"] (ReqArg (\x -> ('w', x)) "EXPR") "Word expression" , Option ['l'] ["lines"] (ReqArg (\x -> ('l', x)) "EXPR") "Line expression"] -- , Option ['f'] ["files"] (ReqArg (\x -> ('f', x)) "EXPR") "File expression" @@ -89,10 +91,10 @@ ocParts :: [OnlyCtx]} deriving (Read, Show, Eq) data OnlyMode = NoMode - | FileMode - | ByteMode String - | CharMode String - | WordMode String + | FileMode -- not implemented + | ByteMode String -- not implemented + | CharMode String -- not implemented + | WordMode String [Char] | LineMode String deriving (Read, Show, Eq) @@ -123,12 +125,14 @@ number = do num <- parseNum return [num] + range :: CharParser () [Int] range = do start <- parseNum char ':' end <- parseNum return [start .. end] + steps :: CharParser () [Int] steps = do start <- parseNum @@ -137,6 +141,7 @@ char ';' step <- parseNum return [start, (start + step) .. end] + nexts :: CharParser () [Int] nexts = do start <- parseNum @@ -151,30 +156,36 @@ where word = do str <- many anyChar return (OnlyExpr [] str []) + number = do abs <- parseNums if abs == [] then word else return (OnlyExpr abs "" []) + regexChar = do ch <- noneOf $ ".,:;" ++ ['A'..'Z'] ++ ['a'..'z'] return ch + regex = do ch <- regexChar pat <- many $ noneOf [ch] char ch return pat - pattIndex = do + + pattIndex = do -- N/regex/M expression abs <- parseNums pat <- regex rel <- parseNums return (OnlyExpr abs pat rel) - pattRange = do + + pattRange = do -- N/begin/:/end/ expression abs <- parseNums pat1 <- regex +-- rel1 <- parseNum -- only one number allowed! char ':' pat2 <- regex - rel <- parseNum -- only one number allowed! - return (OnlyRange abs pat1 pat2 rel) + rel2 <- parseNum -- only one number allowed! + return (OnlyRange abs pat1 pat2 rel2) readRegex :: FilePath -> String -> IO OnlyExpr @@ -234,15 +245,17 @@ notImpl = exitStr ExitSuccess "not implemented" -- option stuff -processOpt :: (Char, String) -> IO () -processOpt (key, value) = +type Opt = (Char, String) +processOpt :: [Opt] -> Opt -> IO () +processOpt opts (key, value) = case key of 'h' -> help 'V' -> showVersion -- 'H' -> helpMan -- 'b' -> modeAdd $ ByteMode value -- 'c' -> modeAdd $ CharMode value - 'w' -> modeAdd $ WordMode value + 'W' -> return () + 'w' -> modeAdd $ WordMode value $ maybe [] id (lookup 'W' opts) 'l' -> modeAdd $ LineMode value -- @@ -265,7 +278,7 @@ case context of OnlyCtx _ [OnlyLeaf] -> case mode of - WordMode expr -> doSep words expr context mode + WordMode expr ch -> doSep (sepWith ch) expr context mode LineMode expr -> doSep lines expr context mode FileMode -> return context OnlyCtx _ ctxs -> do @@ -342,7 +355,7 @@ return (context {ocParts = parts}) simplify mode context = case mode of - WordMode _ -> unSep unwords context + WordMode _ ch -> unSep (unsepWith ch) context LineMode _ -> unSep unlines context _ -> return context @@ -350,9 +363,20 @@ unSep unsep context = return $ context {ocParts = [OnlyLeaf], ocValue = unsep $ map ocValue (ocParts context)} +split :: Eq a => a -> [a] -> [[a]] +split c = map(tail).groupBy(const(c/=)).(c:) + +sepWith :: [Char] -> String -> [String] +sepWith [c] str = split c str +sepWith [] str = words str + +unsepWith :: [Char] -> [String] -> String +unsepWith [c] ls = concat $ intersperse [c] ls +unsepWith [] ls = unwords ls + getIndex :: [a] -> Int -> a -> a getIndex xs n nil = if n < 1 - then xs !! ((length xs) - n) + then xs !! ((length xs) + n) else if n > (length xs) then nil else xs !! (n - 1) @@ -368,7 +392,7 @@ (_, _, err) -> ioError$userError (concat err) -- process options - mapM processOpt opts + mapM (processOpt opts) opts mapM fileAdd nonOpts -- handle some edge cases diff --git a/tests/e-semi.txt b/tests/e-semi.txt new file mode 100644 --- /dev/null +++ b/tests/e-semi.txt @@ -0,0 +1,6 @@ +1;Alfred;This is going to be the longest comment section of them all... +2;Barbra;She has nothing to say. +3;Cheese;Mice love it! +4;Dorsey;The only one who seems to know anything. +5;Edward;Not just a syllable anymore! +6;Finley;Someone who you might not want to meet. diff --git a/tests/i-all.sh b/tests/i-all.sh --- a/tests/i-all.sh +++ b/tests/i-all.sh @@ -2,14 +2,26 @@ BASE="${NAME%.sh}" ONLY="../dist/build/only/only" GREP="grep" +HEAD="head" +TAIL="tail" +CUT="cut" cd "$(dirname $NAME)" function test-eq () { if [ x"$1" = x"$2" ] ; then echo -n PASS + echo " : $BASE" else echo -n FAIL + echo " : $BASE" + echo "---" + echo "$1" + echo "+++" + echo "does not equal:" + echo "---" + echo "$2" + echo "+++" + echo fi - echo " : $BASE" } diff --git a/tests/t-cut-2.sh b/tests/t-cut-2.sh new file mode 100644 --- /dev/null +++ b/tests/t-cut-2.sh @@ -0,0 +1,6 @@ +#!/bin/sh +. i-all.sh + +test-eq \ + "$($CUT -d' ' -f1,2 e-both.txt)" \ + "$($ONLY -l// -w1,2 e-both.txt)" diff --git a/tests/t-cut-semi.sh b/tests/t-cut-semi.sh new file mode 100644 --- /dev/null +++ b/tests/t-cut-semi.sh @@ -0,0 +1,6 @@ +#!/bin/sh +. i-all.sh + +test-eq \ + "$($CUT -d';' -f2 e-semi.txt)" \ + "$($ONLY -l// -W';' -w2 e-semi.txt)" diff --git a/tests/t-eq-no-debug.sh b/tests/t-eq-no-debug.sh new file mode 100644 --- /dev/null +++ b/tests/t-eq-no-debug.sh @@ -0,0 +1,6 @@ +#!/bin/sh +. i-all.sh + +test-eq \ + "$($ONLY e-both.txt -l3)" \ + "3 Cheese - Mice love it!" diff --git a/tests/t-head.sh b/tests/t-head.sh new file mode 100644 --- /dev/null +++ b/tests/t-head.sh @@ -0,0 +1,6 @@ +#!/bin/sh +. i-all.sh + +test-eq \ + "$($HEAD -n3 e-both.txt)" \ + "$($ONLY -l1:3 e-both.txt)" diff --git a/tests/t-tail.sh b/tests/t-tail.sh new file mode 100644 --- /dev/null +++ b/tests/t-tail.sh @@ -0,0 +1,6 @@ +#!/bin/sh +. i-all.sh + +test-eq \ + "$($TAIL -n3 e-both.txt)" \ + "$($ONLY -l-3:-1 e-both.txt)"