2024-10-10

2024-10-10 12:56:56 +08:00
commit 7b347c848a
2648 changed files with 643965 additions and 0 deletions
--- a/core/sim/sim_3_01/Makefile
+++ b/core/sim/sim_3_01/Makefile
@@ -0,0 +1,544 @@
+#	This file is part of the software similarity tester SIM.
+#	Written by Dick Grune, Vrije Universiteit, Amsterdam.
+#	$Id: Makefile,v 2.97 2017-03-19 09:49:29 dick Exp $
+#
+
+VERSION="-DVERSION=\"3.0.1 of 2017-08-15\""
+
+#	E N T R Y   P O I N T S
+
+help:
+	@echo  'Entry points:'
+	@echo  'test:           compile sim_c and run a simple test'
+	@echo  ''
+	@echo  'binaries:       create all binaries'
+	@echo  'exes:           create executables in MSDOS'
+	@echo  'install:        install all binaries'
+	@echo  ''
+	@echo  'view_man:       view sim.pdf'
+	@echo  'lint:           lint sim sources'
+	@echo  'simsim:         run sim_c on the sim sources'
+	@echo  'view_SPC:       view the percentage computation document'
+	@echo  'chklat:         do a LaTeX check on the .tex documents'
+	@echo  ''
+	@echo  'fresh:          remove created files'
+
+#
+# When you modify any of the following macros, do 'make clean'
+#
+
+# System dependencies
+#	=============== including ../lib/sysidf.mk here
+#	This file is part of the auxiliary libraries.
+#	Written by Dick Grune, dick@dickgrune.com
+#	$Id: sysidf.mk,v 1.18 2016-04-22 15:11:58 dick Exp $
+#
+
+################################################################
+# For UNIX-like systems
+
+SYSTEM =	UNIX
+SUBSYSTEM =	SOLARIS
+
+# Locations
+DIR =		/usr
+BINDIR =	$(DIR)/bin.`$(DIR)/bin/arch`
+MAN1DIR =	$(DIR)/man/man1
+
+# Commands
+COPY =		cp -p
+EXE =		.exe#
+LEX =		flex
+LN =		ln
+ZIP =		zip -o
+
+###############################################################
+# General, C compilation:
+CC =		gcc -D$(SYSTEM) -D$(SUBSYSTEM)
+LINT =		lint -ansi -D$(SYSTEM) -D$(SUBSYSTEM)
+LINTFLAGS =	-xh
+
+# General, text:
+LATEX =		pdflatex
+SHOW_PDF =	evince
+SHOW_PDF =	acroread
+SHOW_PDF =	pdfview
+GROFF =		groff -man
+GROFF =		man2pdf
+
+.SUFFIXES:	.1 .3 .pdf
+
+.1.pdf:
+		$(GROFF) $<
+
+.3.pdf:
+		$(GROFF) $<
+#	=============== end of ../lib/sysidf.mk
+
+# Compiling
+MEMORY =	-DMEMCHECK -DMEMCLOBBER
+CFLAGS =	$(VERSION) $(MEMORY) -O4
+LIBFLAGS =	#
+LINTFLAGS =	$(MEMORY) -h# -X
+LOADFLAGS =	-s#			# strip symbol table
+LOADER =	$(CC) $(LOADFLAGS)
+
+# Debugging
+CFLAGS +=	-DDEBUG
+DEBUG_C =	debug.c
+DEBUG_O =	debug.o
+DEBUG_H =	debug.h
+
+#	T E S T   P A R A M E T E R S
+
+# Rumen Stevanov test
+TEST_LANG =	text
+TEST_OPT =	-pPae -r4 -O -t4
+TEST_INP =	Contributors/Rumen_Stefanov/new/*.txt
+
+# slash test
+TEST_LANG =	text
+TEST_OPT =	-r24 -M clang.c pascallang.c "|" textlang.c
+TEST_INP =
+
+# spaced word test
+TEST_LANG =	text
+TEST_OPT =	-r 5
+TEST_INP =	testfiles/test_seplet
+
+# -i option test
+TEST_LANG =	c
+TEST_OPT =	-f -r 20 -R -i <option-i.inp
+TEST_INP =	#
+
+# overlap  test, foo^100 vs. foo^150
+TEST_LANG =	text
+TEST_OPT =	-r50 -p
+TEST_OPT =	-r50
+TEST_INP =	foo_100
+TEST_INP =	foo_100 foo_150
+
+# single file test
+TEST_LANG =	c
+TEST_OPT =	-r24 -M
+TEST_INP =	pass3.c pass3.c	# compares 1st to 2nd, then 2nd to 2nd
+
+# tight match test, foo_100 has exactly 100 tokens
+TEST_LANG =	text
+TEST_OPT =	-r50
+TEST_INP =	foo_100
+
+# percentage test
+TEST_LANG =	c
+TEST_OPT =	-puae
+TEST_INP =	*.l
+
+# larger test
+TEST_LANG =	text
+TEST_OPT =	-r24 -M -puae
+TEST_INP = clang.c textlang.c
+TEST_INP = textlang.c clang.c javalang.c
+
+# test UTF-8 text
+TEST_LANG =	text
+TEST_OPT =	-r12 -MO -T -w80 -d
+TEST_INP =	Korean1.txt Korean2.txt
+
+# test UTF-8 program
+TEST_LANG =	c
+TEST_OPT =	-r12 -MO -w80 -d
+TEST_INP =	utf8test.c utf8test.c
+
+# C++ test
+TEST_LANG =	c++
+TEST_OPT =	-r8 -MO -
+TEST_INP =	c++test.c++ c++test.c++#	# for lack of real C++ files
+
+# test
+TEST_LANG =	c
+TEST_OPT =	-r10 -MO -
+TEST_INP =	clang.c pascallang.c
+TEST_INP =	pass2.c pass1.c
+
+#	I N T R O D U C T I O N
+
+#	Each module (set of programs that together perform some function)
+#	has the following sets of files defined for it:
+#		_SRC	the source files, from which other files derive
+#		_CFS	the C-files, from which the object files derive
+#		_OBJ	object files
+#		_GRB	garbage files produced by the module
+#
+#	(This is a feeble attempt at software-engineering a Makefile.)
+#
+
+test:		sim.res stream.res percentages.res version.res
+
+
+#	B I N A R I E S
+
+BINARIES =	sim_c$(EXE) sim_c++$(EXE) sim_java$(EXE) sim_pasc$(EXE) \
+		sim_m2$(EXE) sim_lisp$(EXE) sim_mira$(EXE) sim_text$(EXE)
+
+binaries:	$(BINARIES)
+
+EXES =		sim_c.exe sim_c++.exe sim_java.exe sim_pasc.exe \
+     		sim_m2.exe sim_lisp.exe sim_mira.exe sim_text.exe
+exes:		$(EXES)
+
+
+#	A U X I L I A R Y   M O D U L E S
+
+# Common modules:
+COM_CFS =	token.c lex.c stream.c text.c tokenarray.c $(DEBUG_C) \
+		ForEachFile.c fname.c Malloc.c any_int.c
+COM_OBJ =	token.o lex.o stream.o text.o tokenarray.o $(DEBUG_O) \
+		ForEachFile.o fname.o Malloc.o any_int.o
+COM_SRC =	token.h lex.h stream.h text.h tokenarray.h $(DEBUG_H) \
+		ForEachFile.h fname.h Malloc.h any_int.h \
+		lang.h language.h \
+		sortlist.spc sortlist.bdy system.par $(COM_CFS)
+
+# C files for the abstract modules:
+ABS_CFS =	lang.c language.c
+
+# The idf module:
+IDF_CFS =	idf.c
+IDF_OBJ =	idf.o
+IDF_SRC =	idf.h $(IDF_CFS)
+
+# The runs package:
+RUNS_CFS =	runs.c percentages.c
+RUNS_OBJ =	runs.o percentages.o
+RUNS_SRC =	runs.h percentages.h $(RUNS_CFS)
+
+# The main program:
+MAIN_CFS =	sim.c options.c newargs.c hash.c compare.c add_run.c \
+		pass1.c pass2.c pass3.c
+MAIN_OBJ =	sim.o options.o newargs.o hash.o compare.o add_run.o \
+		pass1.o pass2.o pass3.o
+MAIN_SRC =	sim.h options.h newargs.h hash.h compare.h add_run.h \
+		pass1.h pass2.h pass3.h \
+		debug.par settings.par $(MAIN_CFS)
+
+sim.o:	 	Makefile	# because of $(VERSION)
+
+# The similarity tester without the language part:
+SIM_CFS =	$(COM_CFS) $(IDF_CFS) $(RUNS_CFS) $(MAIN_CFS)
+SIM_OBJ =	$(COM_OBJ) $(IDF_OBJ) $(RUNS_OBJ) $(MAIN_OBJ)
+SIM_SRC =	$(COM_SRC) $(IDF_SRC) $(RUNS_SRC) $(MAIN_SRC)
+
+
+#	L A N G U A G E S
+
+# The algollike module:
+ALG_CFS =	algollike.c
+ALG_OBJ =	algollike.o
+ALG_SRC =	algollike.h $(ALG_CFS)
+
+# The C Language module:					# C
+CLANG_CFS =	clang.c
+CLANG_OBJ =	clang.o
+CLANG_SRC =	clang.l
+
+clang.c:	clang.l
+		$(LEX) -t clang.l >$@
+
+SIM_C_CFS =	$(SIM_CFS) $(ALG_CFS) $(CLANG_CFS)
+SIM_C_OBJ =	$(SIM_OBJ) $(ALG_OBJ) $(CLANG_OBJ)
+
+sim_c$(EXE):	$(SIM_C_OBJ)
+		$(LOADER) $(SIM_C_OBJ) -o $@
+
+SIM_GRB +=	clang.c sim_c
+
+$(BINDIR)/sim_c$(EXE):	sim_c$(EXE)
+		$(COPY) sim_c$(EXE) $@
+
+# The C++ Language module:					# C++
+C++LANG_CFS =	c++lang.c
+C++LANG_OBJ =	c++lang.o
+C++LANG_SRC =	c++lang.l
+
+c++lang.c:	c++lang.l
+		$(LEX) -t c++lang.l >$@
+
+SIM_C++_CFS =	$(SIM_CFS) $(ALG_CFS) $(C++LANG_CFS)
+SIM_C++_OBJ =	$(SIM_OBJ) $(ALG_OBJ) $(C++LANG_OBJ)
+
+sim_c++$(EXE):	$(SIM_C++_OBJ)
+		$(LOADER) $(SIM_C++_OBJ) -o $@
+
+SIM_GRB +=	c++lang.c sim_c++
+
+$(BINDIR)/sim_c++$(EXE):	sim_c++$(EXE)
+		$(COPY) sim_c++$(EXE) $@
+
+# The Java Language module:					# Java
+JAVALANG_CFS =	javalang.c
+JAVALANG_OBJ =	javalang.o
+JAVALANG_SRC =	javalang.l
+
+javalang.c:	javalang.l
+		$(LEX) -t javalang.l >$@
+
+SIM_JAVA_CFS =	$(SIM_CFS) $(ALG_CFS) $(JAVALANG_CFS)
+SIM_JAVA_OBJ =	$(SIM_OBJ) $(ALG_OBJ) $(JAVALANG_OBJ)
+
+sim_java$(EXE):	$(SIM_JAVA_OBJ)
+		$(LOADER) $(SIM_JAVA_OBJ) -o $@
+
+SIM_GRB +=	javalang.c sim_java
+
+$(BINDIR)/sim_java$(EXE):	sim_java$(EXE)
+		$(COPY) sim_java$(EXE) $@
+
+# The Pascal Language module:					# Pascal
+PASCLANG_CFS =	pascallang.c
+PASCLANG_OBJ =	pascallang.o
+PASCLANG_SRC =	pascallang.l
+
+pascallang.c:	pascallang.l
+		$(LEX) -t pascallang.l >pascallang.c
+
+SIM_PASC_CFS =	$(SIM_CFS) $(ALG_CFS) $(PASCLANG_CFS)
+SIM_PASC_OBJ =	$(SIM_OBJ) $(ALG_OBJ) $(PASCLANG_OBJ)
+
+sim_pasc$(EXE):	$(SIM_PASC_OBJ)
+		$(LOADER) $(SIM_PASC_OBJ) -o $@
+
+SIM_GRB +=	pascallang.c sim_pasc
+
+$(BINDIR)/sim_pasc$(EXE):	sim_pasc$(EXE)
+		$(COPY) sim_pasc$(EXE) $@
+
+# The Modula-2 Language module:					# Modula-2
+M2LANG_CFS =	m2lang.c
+M2LANG_OBJ =	m2lang.o
+M2LANG_SRC =	m2lang.l
+
+m2lang.c:	m2lang.l
+		$(LEX) -t m2lang.l >$@
+
+SIM_M2_CFS =	$(SIM_CFS) $(ALG_CFS) $(M2LANG_CFS)
+SIM_M2_OBJ =	$(SIM_OBJ) $(ALG_OBJ) $(M2LANG_OBJ)
+
+sim_m2$(EXE):	$(SIM_M2_OBJ)
+		$(LOADER) $(SIM_M2_OBJ) -o $@
+
+SIM_GRB +=	m2lang.c sim_m2
+
+$(BINDIR)/sim_m2$(EXE):	sim_m2$(EXE)
+		$(COPY) sim_m2$(EXE) $@
+
+# The Lisp Language module:					# Lisp
+LISPLANG_CFS =	lisplang.c
+LISPLANG_OBJ =	lisplang.o
+LISPLANG_SRC =	lisplang.l
+
+lisplang.c:	lisplang.l
+		$(LEX) -t lisplang.l >$@
+
+SIM_LISP_CFS =	$(SIM_CFS) $(ALG_CFS) $(LISPLANG_CFS)
+SIM_LISP_OBJ =	$(SIM_OBJ) $(ALG_OBJ) $(LISPLANG_OBJ)
+
+sim_lisp$(EXE):	$(SIM_LISP_OBJ)
+		$(LOADER) $(SIM_LISP_OBJ) -o $@
+
+SIM_GRB +=	lisplang.c sim_lisp
+
+$(BINDIR)/sim_lisp$(EXE):	sim_lisp$(EXE)
+		$(COPY) sim_lisp$(EXE) $@
+
+# The Miranda Language module:					# Miranda
+MIRALANG_CFS =	miralang.c
+MIRALANG_OBJ =	miralang.o
+MIRALANG_SRC =	miralang.l
+
+miralang.c:	miralang.l
+		$(LEX) -t miralang.l >$@
+
+SIM_MIRA_CFS =	$(SIM_CFS) $(ALG_CFS) $(MIRALANG_CFS)
+SIM_MIRA_OBJ =	$(SIM_OBJ) $(ALG_OBJ) $(MIRALANG_OBJ)
+
+sim_mira$(EXE):	$(SIM_MIRA_OBJ)
+		$(LOADER) $(SIM_MIRA_OBJ) -o $@
+
+SIM_GRB +=	miralang.c sim_mira
+
+$(BINDIR)/sim_mira$(EXE):	sim_mira$(EXE)
+		$(COPY) sim_mira$(EXE) $@
+
+# The Text module:						# Text
+TEXTLANG_CFS =	textlang.c
+TEXTLANG_OBJ =	textlang.o
+TEXTLANG_SRC =	textlang.l
+
+textlang.c:	textlang.l
+		$(LEX) -t textlang.l >$@
+
+SIM_TEXT_CFS =	$(SIM_CFS) $(TEXTLANG_CFS)
+SIM_TEXT_OBJ =	$(SIM_OBJ) $(TEXTLANG_OBJ)
+
+sim_text$(EXE):	$(SIM_TEXT_OBJ)
+		$(LOADER) $(SIM_TEXT_OBJ) -o $@
+
+SIM_GRB +=	textlang.c sim_text
+
+$(BINDIR)/sim_text$(EXE):	sim_text$(EXE)
+		$(COPY) sim_text$(EXE) $@
+
+
+
+
+
+
+
+
+
+
+
+
+#	T E S T S
+
+# Some simple tests:
+.PHONY:		sim.res percentages.res
+
+sim.res:	sim_$(TEST_LANG)$(EXE) $(TEST_INP)
+		./sim_$(TEST_LANG)$(EXE) $(TEST_OPT) $(TEST_INP)
+
+stream.res:	sim_$(TEST_LANG)$(EXE)
+		./sim_$(TEST_LANG)$(EXE) -- $(TEST_OPT) $(TEST_INP) >$@
+		wc $@ $(TEST_INP)
+TEST_GRB =	stream.res
+
+PERC_TEST_EXE	=	sim_text$(EXE)
+PERC_TEST_FILES =	foo_100 foo_150
+PERC_TEST_EXE	=	sim_c$(EXE)
+PERC_TEST_FILES =	pascallang.l clang.l javalang.l
+percentages.res:$(PERC_TEST_EXE) $(PERC_TEST_FILES)
+		@echo ''
+		./$(PERC_TEST_EXE) -T -p $(PERC_TEST_FILES)
+		@echo ''
+		./$(PERC_TEST_EXE) -T -pa $(PERC_TEST_FILES)
+		@echo ''
+		./$(PERC_TEST_EXE) -T -pae $(PERC_TEST_FILES)
+
+version.res:	sim_$(TEST_LANG)$(EXE)
+		./sim_$(TEST_LANG)$(EXE) -v
+
+
+# More simple tests, using the C version only:
+simsim:		sim_c$(EXE) $(SIM_CFS) $(ALG_CFS)
+		./sim_c$(EXE) -fr 20 $(SIM_CFS) $(ALG_CFS)
+
+# Lint
+lint:		$(SIM_SRC) $(ALG_SRC) $(ABS_CFS)
+		$(LINT) $(LINTFLAGS) $(SIM_CFS) $(ALG_CFS) $(ABS_CFS)
+
+
+#	O T H E R   E N T R I E S
+
+# Documentation
+
+view_man:	sim.pdf
+		$(SHOW_PDF) sim.pdf
+
+%.pdf:		%.tex
+		$(LATEX) $< || log2errmsg <$*.log
+		$(LATEX) $<
+		$(LATEX) $<
+
+SPC =		Similarity_Percentage_Computation
+view_SPC:	$(SPC).pdf
+		$(SHOW_PDF) $(SPC).pdf
+DOCS +=		$(SPC).pdf
+
+# LaTeX checker
+chklat:
+		chklat *.tex
+
+# Installation
+install_all:	install			# just a synonym
+install:	$(MAN1DIR)/sim.1 \
+		$(BINDIR)/sim_c$(EXE) \
+		$(BINDIR)/sim_c++$(EXE) \
+		$(BINDIR)/sim_java$(EXE) \
+		$(BINDIR)/sim_pasc$(EXE) \
+		$(BINDIR)/sim_m2$(EXE) \
+		$(BINDIR)/sim_lisp$(EXE) \
+		$(BINDIR)/sim_mira$(EXE) \
+		$(BINDIR)/sim_text$(EXE)
+
+$(MAN1DIR)/sim.1:	sim.1
+		$(COPY) sim.1 $@
+
+
+# Clean-up
+
+.PHONY:		clean fresh
+clean:
+		-rm -f *.o
+		-rm -f $(SIM_GRB)
+		-rm -f $(TEST_GRB)
+		-rm -f *.aux *.log *.out
+		-rm -f a.out a.exe sim.txt core mon.out
+
+fresh:		clean
+		-rm -f *.exe
+
+#	D E P E N D E N C I E S
+
+# DO NOT DELETE THIS LINE -- make depend depends on it.
+ForEachFile.o: ForEachFile.c ForEachFile.h fname.h
+Malloc.o: Malloc.c any_int.h Malloc.h
+add_run.o: add_run.c sim.h text.h runs.h percentages.h options.h \
+ add_run.h
+algollike.o: algollike.c sim.h options.h token.h algollike.h
+any_int.o: any_int.c any_int.h
+c++lang.o: c++lang.c options.h token.h language.h algollike.h idf.h lex.h \
+ lang.h
+clang.o: clang.c options.h token.h language.h algollike.h idf.h lex.h \
+ lang.h
+compare.o: compare.c sim.h text.h token.h tokenarray.h hash.h language.h \
+ options.h add_run.h compare.h debug.par
+count_sim_dup.o: count_sim_dup.c
+debug.o: debug.c debug.h
+fname.o: fname.c fname.h
+hash.o: hash.c system.par debug.par sim.h text.h Malloc.h any_int.h \
+ token.h language.h tokenarray.h options.h hash.h
+idf.o: idf.c system.par token.h idf.h
+javalang.o: javalang.c options.h token.h language.h algollike.h idf.h \
+ lex.h lang.h
+lang.o: lang.c token.h language.h algollike.h idf.h lex.h lang.h
+language.o: language.c token.h language.h
+lex.o: lex.c lex.h
+lisplang.o: lisplang.c token.h language.h algollike.h lex.h lang.h idf.h
+m.o: m.c
+m2lang.o: m2lang.c options.h token.h language.h algollike.h idf.h lex.h \
+ lang.h
+miralang.o: miralang.c token.h language.h algollike.h lex.h lang.h idf.h
+newargs.o: newargs.c sim.h ForEachFile.h fname.h Malloc.h newargs.h
+options.o: options.c sim.h token.h language.h options.h
+pascallang.o: pascallang.c options.h token.h language.h algollike.h idf.h \
+ lex.h lang.h
+pass1.o: pass1.c debug.par sim.h text.h token.h tokenarray.h lang.h \
+ options.h pass1.h
+pass2.o: pass2.c debug.par sim.h token.h text.h lang.h pass2.h \
+ sortlist.bdy
+pass3.o: pass3.c system.par settings.par debug.par sim.h text.h token.h \
+ runs.h options.h pass3.h percentages.h
+percentages.o: percentages.c debug.par sim.h text.h options.h Malloc.h \
+ percentages.h sortlist.bdy
+runs.o: runs.c sim.h text.h runs.h Malloc.h debug.par sortlist.bdy
+sim.o: sim.c system.par settings.par sim.h options.h newargs.h token.h \
+ tokenarray.h language.h text.h runs.h hash.h compare.h pass1.h pass2.h \
+ pass3.h percentages.h stream.h lang.h Malloc.h any_int.h
+stream.o: stream.c system.par sim.h options.h token.h lang.h stream.h
+t.o: t.c
+text.o: text.c debug.par sim.h token.h stream.h lang.h Malloc.h options.h \
+ text.h
+textlang.o: textlang.c sim.h token.h idf.h lex.h lang.h language.h
+token.o: token.c token.h
+tokenarray.o: tokenarray.c sim.h Malloc.h token.h lang.h tokenarray.h
+utf8test.o: utf8test.c