grep etc

doc/gf-history.html

@@ -14,6 +14,17 @@ Changes in functionality since May 17, 2005, release of GF Version 2.2
 
 <p>
 
+5/10 (AR) Printing missing linearization rules:
+<tt>pm -printer=missing</tt>. Command <tt>g = grep</tt>,
+which works in a way similar to Unix grep.
+
+<p>
+
+5/10 (PL) Printing graphs with function and category dependencies:
+<tt>pg -printer=functiongraph</tt>, <tt>pg -printer=typegraph</tt>.
+
+<p>
+
 20/9 (AR) Added optimization by <b>common subexpression elimination</b>.
 It works on GFC modules and creates <tt>oper</tt> definitions for
 subterms that occur more than once in <tt>lin</tt> definitions. These

examples/gfcc/ImperEng.gf

@@ -1,3 +1,4 @@
+-- # -path=.:prelude
 --# -path=.:../../lib/prelude
 
 -- Toy English phrasing of C programs. Intended use is with 

examples/stoneage/StoneageEng.gf

@@ -1,4 +1,5 @@
---# -path=.:../../lib/resource/abstract:../../lib/resource/english:../../lib/prelude
+--# -path=.:resource/english:resource/abstract:prelude
+-- # -path=.:../../lib/resource/abstract:../../lib/resource/english:../../lib/prelude
 concrete StoneageEng of Stoneage 
   = open SyntaxEng, ResourceEng, ParadigmsEng, SwadeshLexEng,
   StoneageResEng in {

examples/stoneage/StoneageSwe.gf

@@ -1,3 +1,4 @@
+-- # -path=.:resource/abstract:prelude:resource/swedish:resource/scandinavian
 --# -path=.:../../lib/resource/abstract:../../lib/prelude:../../lib/resource/swedish:../../lib/resource/scandinavian
 concrete StoneageSwe of Stoneage 
   = open SyntaxSwe, ResourceSwe, ParadigmsSwe, VerbsSwe, SwadeshLexSwe, StoneageResSwe in {
@@ -30,7 +31,7 @@ lin
   Know = PresVasV2 know_V ;
   Smell s o = PresCl (SPredV2 s (dirV2 känna_V) (DefOneNP 
                            (AdvCN (UseN (mk2N "lukt" "lukter")) 
-                                  (PrepNP possess_Prep o)))) ;
+                                  (AdvPP (PrepNP possess_Prep o))))) ;
   Fear = PresVasV2 fear_V ;
   Kill = PresVasV2 kill_V ;
   Fight s o = PresCl (AdvCl (SPredV s fight_V) (AdvPP (PrepNP with_Prep o))) ;

lib/resource/english/LangEng.gf

@@ -1,5 +1,7 @@
 --# -path=.:../abstract:../../prelude
 
+-- # -path=.:resource/english:resource/abstract:prelude
+
 concrete LangEng of Lang = 
   RulesEng, 
   ClauseEng, 

src/GF/Compile/Compile.hs

@@ -5,9 +5,9 @@
 -- Stability   : (stable)
 -- Portability : (portable)
 --
--- > CVS $Date: 2005/09/20 09:32:56 $
+-- > CVS $Date: 2005/10/05 20:02:19 $
 -- > CVS $Author: aarne $
--- > CVS $Revision: 1.44 $
+-- > CVS $Revision: 1.45 $
 --
 -- The top-level compilation chain from source file to gfc\/gfr.
 -----------------------------------------------------------------------------
@@ -106,7 +106,7 @@ compileModule opts1 st0 file = do
   ps0 <- ioeIO $ pathListOpts opts fpath
 
   let ps1 = if (useFileOpt && not useLineOpt) 
-              then (map (prefixPathName fpath) ps0)
+              then (ps0 ++ map (prefixPathName fpath) ps0)
               else ps0
   ps <- ioeIO $ extendPathEnv gfLibraryPath gfGrammarPathVar ps1
   let ioeIOIf = if oElem beVerbose opts then ioeIO else (const (return ()))

src/GF/Shell.hs

@@ -5,9 +5,9 @@
 -- Stability   : (stable)
 -- Portability : (portable)
 --
--- > CVS $Date: 2005/07/01 08:16:32 $ 
+-- > CVS $Date: 2005/10/05 20:02:19 $ 
 -- > CVS $Author: aarne $
--- > CVS $Revision: 1.42 $
+-- > CVS $Revision: 1.43 $
 --
 -- GF shell command interpreter.
 -----------------------------------------------------------------------------
@@ -51,7 +51,7 @@ import GF.Grammar.PrGrammar
 import Control.Monad (foldM,liftM)
 import System (system)
 import System.Random (newStdGen) ----
-import Data.List (nub)
+import Data.List (nub,isPrefixOf)
 import GF.Data.Zipper ----
 
 import GF.Data.Operations
@@ -269,6 +269,8 @@ execC co@(comm, opts0) sa@((st,(h,_)),a) = checkOptions st co >> case comm of
   CSystemCommand s -> justOutput    opts (system s >> return ()) sa
   CPutString       -> changeArg    (opSS2CommandArg (optStringCommand opts gro)) sa
 -----  CShowTerm        -> changeArg  (opTS2CommandArg (optPrintTerm opts gro) . s2t) sa
+  CGrep ms -> changeArg (AString . unlines . filter (grep ms) . lines . prCommandArg) sa
+
 
   CSetFlag           -> changeState (addGlobalOptions opts0) sa
 ---- deprec!  CSetLocalFlag lang -> changeState (addLocalOptions lang opts0) sa
@@ -327,6 +329,11 @@ execC co@(comm, opts0) sa@((st,(h,_)),a) = checkOptions st co >> case comm of
        then (putStrLn ("Warning: discontinuous category" +++ prt_ c))
        else (return ())
 
+   grep ms s = (if oElem beVerbose opts then not else id) $ grepv ms s --- -v
+   grepv ms s = case s of
+     _:cs -> isPrefixOf ms s || grepv ms cs
+     _ -> isPrefixOf ms s
+
 -- commands either change the state or process the argument, but not both
 -- some commands just do output
 

src/GF/Shell/HelpFile.hs

@@ -5,9 +5,9 @@
 -- Stability   : (stable)
 -- Portability : (portable)
 --
--- > CVS $Date: 2005/09/20 09:32:56 $
+-- > CVS $Date: 2005/10/05 20:02:19 $
 -- > CVS $Author: aarne $
--- > CVS $Revision: 1.13 $
+-- > CVS $Revision: 1.14 $
 --
 -- Help on shell commands. Generated from HelpFile by 'make help'.
 -- PLEASE DON'T EDIT THIS FILE.
@@ -115,7 +115,6 @@ txtHelpFile =
   "\n  options:" ++
   "\n      -utf8  apply UTF8 encoding to the tokens in the grammar" ++
   "\n      -utf8id apply UTF8 encoding to the identifiers in the grammar" ++
-  "\n      -graph print module dependency graph in 'dot' format" ++
   "\n  examples:" ++
   "\n      pm | wf Letter.gfcm  -- print the grammar into the file Letter.gfcm" ++
   "\n      pm -printer=graph | wf D.dot  -- then do 'dot -Tps D.dot > D.ps'" ++
@@ -203,6 +202,14 @@ txtHelpFile =
   "\n  examples:" ++
   "\n     tt -lexer=codelit \"2*(x + 3)\"  -- a favourite lexer for program code" ++
   "\n" ++
+  "\ng, grep: g String1 String2" ++
+  "\n      Grep the String1 in the String2. String2 is read line by line," ++
+  "\n      and only those lines that contain String1 are returned." ++
+  "\n  flags:" ++
+  "\n     -v  return those lines that do not contain String1." ++
+  "\n  examples:" ++
+  "\n     pg -printer=cf | grep \"mother\"  -- show cf rules with word mother" ++
+  "\n" ++
   "\ncc, compute_concrete: cc Term" ++
   "\n      Compute a term by concrete syntax definitions. Uses the topmost" ++
   "\n      resource module (the last in listing by command po) to resolve " ++
@@ -505,13 +512,16 @@ txtHelpFile =
   "\n    -optimize=all          first try parametrize then do values with the rest" ++
   "\n    -optimize=none         no optimization" ++
   "\n" ++
-  "\n-parser, parsing strategy. The default is chart. If -cfg or -mcfg are selected, only bottomup and topdown are recognized." ++
+  "\n-parser, parsing strategy. The default is chart. If -cfg or -mcfg are" ++
+  "\n       selected, only bottomup and topdown are recognized." ++
   "\n    -parser=chart          bottom-up chart parsing" ++
   "\n    -parser=bottomup       a more up to date bottom-up strategy" ++
   "\n    -parser=topdown        top-down strategy" ++
   "\n    -parser=old            an old bottom-up chart parser" ++
   "\n" ++
-  "\n-printer, format in which the grammar is printed. The default is gfc." ++
+  "\n-printer, format in which the grammar is printed. The default is" ++
+  "\n       gfc. Those marked with M are (only) available for pm, the rest" ++
+  "\n       for pg." ++
   "\n    -printer=gfc            GFC grammar" ++
   "\n    -printer=gf             GF grammar" ++
   "\n    -printer=old            old GF grammar" ++
@@ -535,6 +545,15 @@ txtHelpFile =
   "\n    -printer=fa_graphviz    a finite automaton with labelled edges" ++
   "\n    -printer=regular        a regular grammar in a simple BNF" ++
   "\n    -printer=unpar          a gfc grammar with parameters eliminated" ++
+  "\n    -printer=functiongraph  abstract syntax functions in 'dot' format" ++
+  "\n    -printer=typegraph      abstract syntax categories in 'dot' format" ++
+  "\n    -printer=gfcm        M  gfcm file (default for pm)" ++
+  "\n    -printer=header      M  gfcm file with header (for GF embedded in Java)" ++
+  "\n    -printer=graph       M  module dependency graph in 'dot' (graphviz) format" ++
+  "\n    -printer=missing     M  the missing linearizations of each concrete" ++
+  "\n    -printer=gfc-prolog  M  gfc in prolog format (also pg)" ++
+  "\n    -printer=mcfg-prolog M  mcfg in prolog format (also pg)" ++
+  "\n    -printer=cfg-prolog  M  cfg in prolog format (also pg)" ++
   "\n" ++
   "\n-startcat, like -cat, but used in grammars (to avoid clash with keyword cat)" ++
   "\n" ++

src/GF/Shell/PShell.hs

@@ -5,9 +5,9 @@
 -- Stability   : (stable)
 -- Portability : (portable)
 --
--- > CVS $Date: 2005/06/20 16:14:20 $ 
+-- > CVS $Date: 2005/10/05 20:02:20 $ 
 -- > CVS $Author: aarne $
--- > CVS $Revision: 1.25 $
+-- > CVS $Revision: 1.26 $
 --
 -- parsing GF shell commands. AR 11\/11\/2001
 -----------------------------------------------------------------------------
@@ -133,6 +133,7 @@ pCommand ws = case ws of
   "st" : s      -> aTerm   CShowTerm s
   "!"  : s      -> aUnit   (CSystemCommand (unwords s))
   "sc" : s      -> aUnit   (CSystemCommand (unwords s))
+  "g"  : f : s  -> aString (CGrep (unquote f)) s
   
   "sf" : l : [] -> aUnit (CSetLocalFlag (language l))
   "sf" : []     -> aUnit CSetFlag

src/GF/Shell/ShellCommands.hs

@@ -5,9 +5,9 @@
 -- Stability   : (stable)
 -- Portability : (portable)
 --
--- > CVS $Date: 2005/07/01 08:16:32 $ 
+-- > CVS $Date: 2005/10/05 20:02:20 $ 
 -- > CVS $Author: aarne $
--- > CVS $Revision: 1.39 $
+-- > CVS $Revision: 1.40 $
 --
 -- The datatype of shell commands and the list of their options.
 -----------------------------------------------------------------------------
@@ -64,6 +64,7 @@ data Command =
  | CPutString
  | CShowTerm
  | CSystemCommand String
+ | CGrep String
 
  | CSetFlag
  | CSetLocalFlag Language
@@ -193,6 +194,7 @@ optionsOfCommand co = case co of
   CShowTerm -> flags "printer"
   CShowTreeGraph -> opts "c f g o"
   CSystemCommand _ -> none
+  CGrep _ -> opts "v"
 
   CPrintGrammar -> both "utf8" "printer lang"
   CPrintMultiGrammar -> both "utf8 utf8id" "printer"

src/GF/UseGrammar/Custom.hs

@@ -5,9 +5,9 @@
 -- Stability   : (stable)
 -- Portability : (portable)
 --
--- > CVS $Date: 2005/10/05 11:56:42 $ 
+-- > CVS $Date: 2005/10/05 20:02:20 $ 
--- > CVS $Author: peb $
+-- > CVS $Author: aarne $
--- > CVS $Revision: 1.76 $
+-- > CVS $Revision: 1.77 $
 --
 -- A database for customizable GF shell commands. 
 --
@@ -63,6 +63,7 @@ import GF.Data.Zipper
 
 import GF.UseGrammar.Statistics
 import GF.UseGrammar.Morphology
+import GF.UseGrammar.Information
 import GF.API.GrammarToHaskell
 -----import GrammarToCanon (showCanon, showCanonOpt)
 -----import qualified GrammarToGFC as GFC
@@ -307,6 +308,7 @@ customMultiGrammarPrinter =
   ,(strCI "header", const (MC.prCanonMGr . unoptimizeCanon))
   ,(strCI "cfgm", prCanonAsCFGM)
   ,(strCI "graph", visualizeCanonGrammar)
+  ,(strCI "missing", const missingLinCanonGrammar)
 
 -- to prolog format:
   ,(strCI "gfc-prolog", CnvProlog.prtSMulti)

src/GF/UseGrammar/Information.hs

@@ -5,16 +5,19 @@
 -- Stability   : (stable)
 -- Portability : (portable)
 --
--- > CVS $Date: 2005/05/30 18:39:45 $ 
+-- > CVS $Date: 2005/10/05 20:02:20 $ 
 -- > CVS $Author: aarne $
--- > CVS $Revision: 1.6 $
+-- > CVS $Revision: 1.7 $
 --
 -- information on module, category, function, operation, parameter,... 
 -- AR 16\/9\/2003.
 -- uses source grammar
 -----------------------------------------------------------------------------
 
-module GF.UseGrammar.Information (showInformation) where
+module GF.UseGrammar.Information (
+   showInformation,
+   missingLinCanonGrammar
+   ) where
 
 import GF.Grammar.Grammar
 import GF.Infra.Ident
@@ -25,6 +28,7 @@ import GF.CF.PPrCF
 import GF.Compile.ShellState
 import GF.Grammar.PrGrammar
 import GF.Grammar.Lookup
+import GF.Grammar.Macros (zIdent)
 import qualified GF.Canon.GFC as GFC
 import qualified GF.Canon.AbsGFC as AbsGFC
 
@@ -141,3 +145,11 @@ ownConstants = map fst . filter isOwn . tree2list where
     AnyInd _ _ -> False
     _ -> True
 
+missingLinCanonGrammar :: GFC.CanonGrammar -> String
+missingLinCanonGrammar cgr = 
+  unlines $ concat [prt_ c : missing js | (c,js) <- concretes] where
+  missing js = map (("  " ++) . prt_) $ filter (not . flip isInBinTree js) abstract
+  abstract = err (const []) (map fst . tree2list . jments) $ lookupModMod cgr absId
+  absId = maybe (zIdent "") id $ greatestAbstract cgr
+  concretes = [(cnc,jments mo) | 
+    cnc <- allConcretes cgr absId, Ok mo <- [lookupModMod cgr cnc]]

src/HelpFile

@@ -86,7 +86,6 @@ pm, print_multigrammar: pm
   options:
       -utf8  apply UTF8 encoding to the tokens in the grammar
       -utf8id apply UTF8 encoding to the identifiers in the grammar
-      -graph print module dependency graph in 'dot' format
   examples:
       pm | wf Letter.gfcm  -- print the grammar into the file Letter.gfcm
       pm -printer=graph | wf D.dot  -- then do 'dot -Tps D.dot > D.ps'
@@ -174,6 +173,14 @@ tt, test_tokenizer: tt String
   examples:
      tt -lexer=codelit "2*(x + 3)"  -- a favourite lexer for program code
 
+g, grep: g String1 String2
+      Grep the String1 in the String2. String2 is read line by line,
+      and only those lines that contain String1 are returned.
+  flags:
+     -v  return those lines that do not contain String1.
+  examples:
+     pg -printer=cf | grep "mother"  -- show cf rules with word mother
+
 cc, compute_concrete: cc Term
       Compute a term by concrete syntax definitions. Uses the topmost
       resource module (the last in listing by command po) to resolve 
@@ -476,13 +483,16 @@ q, quit: q
     -optimize=all          first try parametrize then do values with the rest
     -optimize=none         no optimization
 
--parser, parsing strategy. The default is chart. If -cfg or -mcfg are selected, only bottomup and topdown are recognized.
+-parser, parsing strategy. The default is chart. If -cfg or -mcfg are
+       selected, only bottomup and topdown are recognized.
     -parser=chart          bottom-up chart parsing
     -parser=bottomup       a more up to date bottom-up strategy
     -parser=topdown        top-down strategy
     -parser=old            an old bottom-up chart parser
 
--printer, format in which the grammar is printed. The default is gfc.
+-printer, format in which the grammar is printed. The default is
+       gfc. Those marked with M are (only) available for pm, the rest
+       for pg.
     -printer=gfc            GFC grammar
     -printer=gf             GF grammar
     -printer=old            old GF grammar
@@ -506,6 +516,15 @@ q, quit: q
     -printer=fa_graphviz    a finite automaton with labelled edges
     -printer=regular        a regular grammar in a simple BNF
     -printer=unpar          a gfc grammar with parameters eliminated
+    -printer=functiongraph  abstract syntax functions in 'dot' format
+    -printer=typegraph      abstract syntax categories in 'dot' format
+    -printer=gfcm        M  gfcm file (default for pm)
+    -printer=header      M  gfcm file with header (for GF embedded in Java)
+    -printer=graph       M  module dependency graph in 'dot' (graphviz) format
+    -printer=missing     M  the missing linearizations of each concrete
+    -printer=gfc-prolog  M  gfc in prolog format (also pg)
+    -printer=mcfg-prolog M  mcfg in prolog format (also pg)
+    -printer=cfg-prolog  M  cfg in prolog format (also pg)
 
 -startcat, like -cat, but used in grammars (to avoid clash with keyword cat)