v0.99.2

       - build process with automake && autoconfig && configure for flop and
         cheap, boost and dumpgram binaries may be revived if used by anybody 
       - adaptation of source files to use automatically build config.h
       - make the use of ICU really optional, i.e., make cheap work
         without ICU on demand.
       - corpus approximation (jxchg) output format provided anew
       - separate switches for unification and subsumption quickcheck
         computation
       - changed version mechanism to be supported by the auto... tools


git-svn-id: https://pet.opendfki.de/repos/pet/main@225 4200e16c-5112-0410-ac55-d7fb557a720a

BUGS

@@ -1,7 +1,6 @@
 - the bound on the number of inflection rules (setting max-inflections) does 
   not work
 - flop is not able to dump cyclic structures
-- Berthold: packing vs. Relativsaetze (what is the exact error?)
 
 - wrong/no characterization when unfilling is used
   :-( No clean way to implement this; in fact, characterization should be 

CHANGELOG

@@ -1,3 +1,13 @@
+v0.99.2
+  - build process with automake && autoconfig && configure for flop and cheap,
+    boost and dumpgram binaries may be revived if used by anybody
+  - adaptation of source files to use automatically build config.h
+  - make the use of ICU really optional, i.e. make cheap work without ICU 
+    altogether. 
+  - corpus approximation (jxchg) output format provided anew
+  - separate switches for unification and subsumption quickcheck computation
+  - changed version mechanism to be supported by the auto... tools
+
 v0.99.1
   - make XML input mode really optional, fixes in Makefile and cheap.cpp
 
@@ -22,7 +32,7 @@ v0.99.0
   - activation of packing without restrictor setting does no longer lead to a
     segmentation fault; packing is simply not activated.
   - translation of iso chars to isomorphix in YY input mode
-  - incr(tsdb[]) file dump mode
+  - [incr tsdb()] file dump mode
   - version string now included in flop and cheap binaries. version number is
     printed with usage information
   - printer for hierarchies in VCG tool style, can be used in cheap and flop
@@ -38,8 +48,8 @@ v0.99.0
 
 Done previously (from old ToDo file, partially redundant)
 
-+- XML input mode
-  + complete DTD specification (Uli S. and me did this)
++ XML input mode
+  + complete DTD specification (Uli S. and bk did this)
   + build SAX parser
   + supersedes integration of bernd's (whiteboard) version
 
@@ -72,20 +82,9 @@ Done previously (from old ToDo file, partially redundant)
 + Restricting the number of inflection rule applications
 
 + positions and counts for YY and XML tokenizer
-+ perforce main branch auf den neuesten Stand bringen:
-  raus:
-     cheap:
-        agenda.cpp inputchart.cpp/h inputtoken.cpp/h chartpositions.h
-        tokenizer.cpp/h parser.cpp/h mrs.cpp/h  
-     common:
-        errors.cpp
-
-  neu:
-     cheap:
-        xmlparser* xml-tokenizer* pic-handler* pic-states.h lexparser.*
-     common:
-        hashing.h vcg_print.h version.h
 
 + japanese multiword bug (requires input chart redesign)
 +? implement mrs/rmrs code - processor interface ?Is this implemented or not?
 
++ yy_tokenizer removed from yy.cpp
++ runtime selection of online-morphology vs full-forms

Makefile.am

@@ -0,0 +1,24 @@
+SUBDIRS      = flop cheap
+DIST_SUBDIRS = $(SUBDIRS) common borland
+EXTRA_DIST   = BUGS CHANGELOG LICENSE README TODO \
+	       doxyconfig.cheap doxyconfig.flop
+
+# For ebrowse (Emacs)
+BROWSE: 
+	echo `find $(topsrc_dir) -name '*.h' -print ` \
+	     `find $(topsrc_dir) \( -name '*.c' -o -name '*.cpp' \) -print` | \
+	tr ' ' '\n'| ebrowse
+
+sign: dist
+	gpg --detach-sign --armor $(distdir).tar.gz
+	md5sum $(distdir).tar.gz | gpg --clearsign > $(distdir).tar.gz.md5sum
+
+# Dependencies: all source files of the distribution
+# Should be done when the distribution is made
+doc: flopdoc cheapdoc
+
+flopdoc:
+	doxygen doxyconfig.flop
+
+cheapdoc:
+	doxygen doxyconfig.cheap

TODO

@@ -1,6 +1,11 @@
-- build process: auto(config|make)
+- restrictors that are paths instead of features
 
-- cheap dynamic library / API
+- API!!! and maybe cheap dynamic library
+  - restarting a parse stopped because the first result arrived
+  - determining the subset of results to retrieve
+  - determine the desired output format(s) (multiple formats may be desired, 
+    without reparse!)
+  - set/change options/settings through API (a part of "clean up:options")
 
 - flop returns zero even in the presence of errors like non-unique feature
   introduction
@@ -19,16 +24,12 @@
 
 - more flexible heuristics / better selection of partial results
 
-- separate switches for unification and subsumption quickcheck computation
-
 - cleaning up:
   - option handling
+  - logging / debugging info: get rid of global verbosity,
+    implement some central logging facility (take Apache log4cxx)
   - YY references; split yy.cpp module into separate modules
-    + yy_tokenizer removed from yy.cpp
     - server mode still unused, yy.cpp/h should become socket.cpp/h
-  + runtime selection of online-morphology vs full-forms
-  - logging / debugging info: get rid of global verbosity,
-    implement some central logging facility (take log4cxx)
 
 - complete lexical database (postgres) integration
 
@@ -67,8 +68,6 @@
   - val(path1) OP const1 && val(path1) OP val(path2)
   - val(path1) OP val(path2) && val(path2) OP const2  (??)
 
-- restrictors that are paths instead of features
-
 refactoring:
 - make tAgenda a template
 - make the unification engine(s) more modular

cheap/Jamfile.in

@@ -0,0 +1,132 @@
+UNIFIER = tomabechi ;
+YY = true ;
+
+TSDB = true ;
+ITSDBDIR = @ITSDBDIR@ ;
+
+ICU = true ;
+ICUDIR = @ICUDIR@ ; 
+
+PSQLLEX = false ;
+
+ECL = true ;
+
+ROBUST = true ;
+#ROBUST = false ;
+#PROFILE = -pg ;
+
+CC = @CC@ ;
+C++ = @CXX@ ;
+
+# -g -a -pg are for debugging and profiling
+C++FLAGS += -g $(PROFILE) -Wall ;
+CFLAGS += -g $(PROFILE) -Wall ;
+
+LINK = g++ ;
+OPTIM = -O3 ;
+
+SEARCH_SOURCE += ../common ;
+
+if $(UNIFIER) = tomabechi
+{
+  DAGSOURCES = dag-io.cpp dag-common.cpp dag-arced.cpp dag-alloc.cpp
+	       dag-tomabechi.cpp failure.cpp qc.cpp ;
+  DAGFLAGS = -DDAG_TOMABECHI -DQC_PATH_COMP ;
+}
+else if $(UNIFIER) = simple
+{
+  DAGSOURCES = dag-io.cpp dag-common.cpp dag-arced.cpp dag-alloc.cpp
+	       dag-simple.cpp ;
+  DAGFLAGS = -DDAG_SIMPLE -DWROBLEWSKI2 ;
+}
+
+if $(ROBUST) = true
+{
+  DAGFLAGS += -DROBUST -DMARK_PERMANENT ;
+  DAGSOURCES += rcu-types.cpp dag-chunk-alloc.cpp ;
+}
+
+COMMONSOURCES = bitcode.cpp chunk-alloc.cpp errors.cpp mfile.c
+        	lex-io.cpp lex-tdl.cpp settings.cpp fs.cpp dumper.cpp
+                grammar-dump.cpp grammar.cpp types.cpp tsdb++.cpp
+                utility.cpp hash.cpp ;
+
+PARSESOURCES = parse.cpp lexicon.cpp item.cpp task.cpp chart.cpp
+	       agenda.cpp tokenizer.cpp options.cpp postags.cpp
+               inputtoken.cpp inputchart.cpp paths.cpp mrs.cpp sm.cpp ;
+
+CHEAPSOURCES = cheap.cpp $(DAGSOURCES) $(COMMONSOURCES) $(PARSESOURCES) ;
+
+C++FLAGS += $(DAGFLAGS) ;
+
+if $(TSDB) = true
+{
+  C++FLAGS += -DTSDBAPI -DTSDBFILEAPI -DSOCKET_INTERFACE ;
+  HDRS += $(ITSDBDIR)/include ;
+}
+
+if $(ICU) = true
+{
+  C++FLAGS += -DICU -DONLINEMORPH ;
+  HDRS += $(ICUDIR)/include ;
+  CHEAPSOURCES += unicode.cpp morph.cpp ;
+}
+
+if $(YY) = true
+{
+  CHEAPSOURCES += k2y.cpp yy.cpp ;
+  C++FLAGS += -DYY ;
+}
+
+if $(PSQLLEX) = true
+{
+  CHEAPSOURCES += psqllex.cpp ;
+  C++FLAGS += -DPSQLLEX ;
+}
+
+if $(ECL) = true
+{
+  CHEAPSOURCES += petecl.c petmrs.c cppbridge.cpp ;
+  HDRS += /proj/contrib/lib/ecl/h ;
+  C++FLAGS += -DECL ;
+  CCFLAGS on petecl.o += -Dlinux -fstrict-aliasing ;
+  CCFLAGS on rmrs.o += -Dlinux -fstrict-aliasing ;
+}
+
+C++FLAGS += -DHASH_MAP_AVAIL -DUSEMMAP ;
+
+HDRS += . ;
+
+LINKLIBS on cheap = -lm -lstdc++ -liberty $(PROFILE) ;
+
+if $(TSDB) = true
+{
+  LINKFLAGS on cheap += -L$(ITSDBDIR)/lib/linux -Xlinker -rpath -Xlinker $(ITSDBDIR)/lib/linux ;
+  LINKLIBS on cheap += -litsdb -lpvm3 ;
+}
+
+if $(ICU) = true
+{
+  LINKFLAGS on cheap += -L$(ICUDIR)/lib -Xlinker -rpath -Xlinker $(ICUDIR)/lib ;
+  LINKLIBS on cheap += -licuuc -licui18n -licudata -lpthread -ldl ;
+}
+
+if $(LEXDB) = true
+{
+  LINKLIBS on cheap += -lpq ;
+}
+
+if $(ECL) = true
+{
+  LINKLIBS on cheap += -lecl -lclos -llsp -lgc -ldl -lgmp -lmrs ;
+  LINKFLAGS on cheap += -L/proj/contrib/lib/ecl -Wl,--export-dynamic ;
+}
+
+Main cheap : $(CHEAPSOURCES) ; 
+
+
+if $(TSDB) = false
+{
+  DUMPGRAMSOURCES = dumpgram.cpp errors.cpp grammar-dump.cpp dumper.cpp ;
+  Main dumpgram : $(DUMPGRAMSOURCES) ;
+}