langscan 1.2

data/ext/langscan/java/java/javatok.l

@@ -0,0 +1,155 @@
+/*
+ * java.l - a lex rule for Java
+ * 
+ * Copyright (C) 2005 Keisuke Nishida <knishida@open-cobol.org>
+ *     All rights reserved.
+ *     This is free software with ABSOLUTELY NO WARRANTY.
+ * 
+ * You can redistribute it and/or modify it under the terms of 
+ * the GNU General Public License version 2.
+ */
+
+%option reentrant
+%option prefix="langscan_java_lex_"
+%option noyywrap
+%option nodefault
+%s CLASSDEF
+
+
+slash           \/
+star            \*
+nonstar         [^\*]
+nonslashstar    [^\/\*]
+commentcontent  {star}+{nonslashstar}{nonstar}*
+comment         {slash}{star}{nonstar}*{commentcontent}*{star}+{slash}
+whitespace      [ \t\f\r\n]|{comment}
+
+id              [A-Za-z_][0-9A-Za-z_]*
+%{
+
+#include "java.h"
+
+#define YY_EXTRA_TYPE langscan_java_lex_extra_t *
+
+#if YY_NULL != 0
+#error "YY_NULL is not 0."
+#endif
+
+#define YY_DECL langscan_java_token_t langscan_java_lex_lex(yyscan_t yyscanner)
+
+#define YY_INPUT(buf,result,max_size) \
+  if (!yyextra->eof) { \
+    result = yyextra->user_read(&(yyextra->user_data), (buf), (max_size)); \
+    if (result == 0) \
+      yyextra->eof = 1; \
+  }
+
+#define UPD update_pos(yyextra, yytext, yyleng)
+static void update_pos(langscan_java_lex_extra_t *, char *, int);
+
+#define report(token) \
+  do { \
+    yyextra->text = yytext; \
+    yyextra->leng = yyleng; \
+    return langscan_java_##token; \
+  } while (0)
+
+%}
+
+%%
+
+class/{whitespace}+{id} { UPD; BEGIN(CLASSDEF); report(ident); }
+<CLASSDEF>{id}          { UPD; BEGIN(INITIAL); report(classdef); }
+
+[ \t\f\r]+              { UPD; report(space); }
+\n                      { UPD; report(space); }
+"//".*			{ UPD; report(comment); }
+{comment}		{ UPD; report(comment); }
+\"([^\\\"]|\\.)*\"	{ UPD; report(string); }
+{id}                    { UPD; report(ident); }
+.			{ UPD; report(punct); }
+
+%%
+
+static void update_pos(
+  langscan_java_lex_extra_t *extra,
+  char *text,
+  int leng)
+{
+  int i, j;
+  extra->beg_byteno = extra->end_byteno;
+  extra->beg_lineno = extra->end_lineno;
+  extra->beg_columnno = extra->end_columnno;
+  j = 0;
+  for (i = 0; i < leng; i++) {
+    if (text[i] == '\n') {
+      extra->end_lineno++;
+      j = i + 1;
+      extra->end_columnno = 0;
+    }
+  }
+  extra->end_columnno += leng - j;
+  extra->end_byteno += leng;
+}
+
+langscan_java_tokenizer_t *langscan_java_make_tokenizer(
+  size_t (*user_read)(void **user_data_p, char *buf, size_t maxlen),
+  void *user_data)
+{
+  langscan_java_tokenizer_t *tokenizer;
+  langscan_java_lex_extra_t *extra;
+  tokenizer = (langscan_java_tokenizer_t *)malloc(sizeof(langscan_java_tokenizer_t));
+  if (tokenizer == NULL)
+    return NULL;
+  extra = (langscan_java_lex_extra_t *)malloc(sizeof(langscan_java_lex_extra_t));
+  if (extra == NULL)
+    return NULL;
+  extra->user_read = user_read;
+  extra->user_data = user_data;
+  extra->beg_lineno = 1;
+  extra->beg_columnno = 0;
+  extra->beg_byteno = 0;
+  extra->end_lineno = 1;
+  extra->end_columnno = 0;
+  extra->end_byteno = 0;
+  extra->eof = 0;
+  tokenizer->extra = extra;
+  langscan_java_lex_lex_init(&tokenizer->scanner);
+  langscan_java_lex_set_extra(extra, tokenizer->scanner);
+  return tokenizer;
+}
+
+langscan_java_token_t langscan_java_get_token(langscan_java_tokenizer_t *tokenizer) 
+{
+  return langscan_java_lex_lex(tokenizer->scanner);
+}
+
+void langscan_java_free_tokenizer(langscan_java_tokenizer_t *tokenizer) 
+{
+  langscan_java_lex_extra_t *extra = langscan_java_lex_get_extra(tokenizer->scanner);
+  free((void *)extra);
+  langscan_java_lex_lex_destroy(tokenizer->scanner);
+  free((void *)tokenizer);
+}
+
+user_read_t langscan_java_tokenizer_get_user_read(langscan_java_tokenizer_t *tokenizer)
+{
+  return tokenizer->extra->user_read;
+}
+
+void *langscan_java_tokenizer_get_user_data(langscan_java_tokenizer_t *tokenizer)
+{
+  return tokenizer->extra->user_data;
+}
+
+const char *langscan_java_token_name(langscan_java_token_t token)
+{
+  static char *token_names[] = {
+    "*eof*",
+#define LANGSCAN_JAVA_TOKEN(name) #name,
+    LANGSCAN_JAVA_TOKEN_LIST
+#undef LANGSCAN_JAVA_TOKEN
+  };
+
+  return token_names[token];
+}

data/ext/langscan/java/java/modulename.txt

@@ -0,0 +1 @@
+Java

data/ext/langscan/java/java/tokenlist.txt

@@ -0,0 +1,11 @@
+preproc_beg
+preproc_end
+character
+integer
+floating
+string
+ident
+punct
+comment
+space
+classdef

data/ext/langscan/javascript/javascript/Makefile

@@ -0,0 +1,157 @@
+
+SHELL = /bin/sh
+
+#### Start of system configuration section. ####
+
+srcdir = /Users/osuka/devel/git/langscan/ext/langscan/javascript/javascript
+topdir = /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/universal-darwin10.0
+hdrdir = $(topdir)
+VPATH = $(srcdir):$(topdir):$(hdrdir)
+exec_prefix = $(prefix)
+prefix = $(DESTDIR)/System/Library/Frameworks/Ruby.framework/Versions/1.8/usr
+sharedstatedir = $(prefix)/com
+mandir = $(DESTDIR)/usr/share/man
+psdir = $(docdir)
+oldincludedir = $(DESTDIR)/usr/include
+localedir = $(datarootdir)/locale
+bindir = $(exec_prefix)/bin
+libexecdir = $(exec_prefix)/libexec
+sitedir = $(DESTDIR)/Library/Ruby/Site
+htmldir = $(docdir)
+vendorarchdir = $(vendorlibdir)/$(sitearch)
+includedir = $(prefix)/include
+infodir = $(DESTDIR)/usr/share/info
+vendorlibdir = $(vendordir)/$(ruby_version)
+sysconfdir = $(prefix)/etc
+libdir = $(exec_prefix)/lib
+sbindir = $(exec_prefix)/sbin
+rubylibdir = $(libdir)/ruby/$(ruby_version)
+docdir = $(datarootdir)/doc/$(PACKAGE)
+dvidir = $(docdir)
+vendordir = $(libdir)/ruby/vendor_ruby
+datarootdir = $(prefix)/share
+pdfdir = $(docdir)
+archdir = $(rubylibdir)/$(arch)
+sitearchdir = $(sitelibdir)/$(sitearch)
+datadir = $(datarootdir)
+localstatedir = $(prefix)/var
+sitelibdir = $(sitedir)/$(ruby_version)
+
+CC = gcc
+LIBRUBY = $(LIBRUBY_SO)
+LIBRUBY_A = lib$(RUBY_SO_NAME)-static.a
+LIBRUBYARG_SHARED = -l$(RUBY_SO_NAME)
+LIBRUBYARG_STATIC = -l$(RUBY_SO_NAME)
+
+RUBY_EXTCONF_H = 
+CFLAGS   =  -fno-common -arch i386 -arch x86_64 -g -Os -pipe -fno-common -DENABLE_DTRACE  -fno-common  -pipe -fno-common $(cflags) 
+INCFLAGS = -I. -I$(topdir) -I$(hdrdir) -I$(srcdir)
+DEFS     = 
+CPPFLAGS =   -D_XOPEN_SOURCE -D_DARWIN_C_SOURCE $(DEFS) $(cppflags)
+CXXFLAGS = $(CFLAGS) 
+ldflags  = -L. -arch i386 -arch x86_64 
+dldflags = 
+archflag = 
+DLDFLAGS = $(ldflags) $(dldflags) $(archflag)
+LDSHARED = cc -arch i386 -arch x86_64 -pipe -bundle -undefined dynamic_lookup
+AR = ar
+EXEEXT = 
+
+RUBY_INSTALL_NAME = ruby
+RUBY_SO_NAME = ruby
+arch = universal-darwin10.0
+sitearch = universal-darwin10.0
+ruby_version = 1.8
+ruby = /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/bin/ruby
+RUBY = $(ruby)
+RM = rm -f
+MAKEDIRS = mkdir -p
+INSTALL = /usr/bin/install -c
+INSTALL_PROG = $(INSTALL) -m 0755
+INSTALL_DATA = $(INSTALL) -m 644
+COPY = cp
+
+#### End of system configuration section. ####
+
+preload = 
+
+libpath = . $(libdir)
+LIBPATH =  -L. -L$(libdir)
+DEFFILE = 
+
+CLEANFILES = mkmf.log
+DISTCLEANFILES = 
+
+extout = 
+extout_prefix = 
+target_prefix = /langscan/javascript
+LOCAL_LIBS = 
+LIBS = $(LIBRUBYARG_SHARED)  -lpthread -ldl  
+SRCS = javascript.c javascripttok.c
+OBJS = javascript.o javascripttok.o
+TARGET = javascript
+DLLIB = $(TARGET).bundle
+EXTSTATIC = 
+STATIC_LIB = 
+
+BINDIR        = $(bindir)
+RUBYCOMMONDIR = $(sitedir)$(target_prefix)
+RUBYLIBDIR    = $(sitelibdir)$(target_prefix)
+RUBYARCHDIR   = $(sitearchdir)$(target_prefix)
+
+TARGET_SO     = $(DLLIB)
+CLEANLIBS     = $(TARGET).bundle $(TARGET).il? $(TARGET).tds $(TARGET).map
+CLEANOBJS     = *.o *.a *.s[ol] *.pdb *.exp *.bak
+
+all:		$(DLLIB)
+static:		$(STATIC_LIB)
+
+clean:
+		@-$(RM) $(CLEANLIBS) $(CLEANOBJS) $(CLEANFILES)
+
+distclean:	clean
+		@-$(RM) Makefile $(RUBY_EXTCONF_H) conftest.* mkmf.log
+		@-$(RM) core ruby$(EXEEXT) *~ $(DISTCLEANFILES)
+
+realclean:	distclean
+install: install-so install-rb
+
+install-so: $(RUBYARCHDIR)
+install-so: $(RUBYARCHDIR)/$(DLLIB)
+$(RUBYARCHDIR)/$(DLLIB): $(DLLIB)
+	$(INSTALL_PROG) $(DLLIB) $(RUBYARCHDIR)
+install-rb: pre-install-rb install-rb-default
+install-rb-default: pre-install-rb-default
+pre-install-rb: Makefile
+pre-install-rb-default: Makefile
+$(RUBYARCHDIR):
+	$(MAKEDIRS) $@
+
+site-install: site-install-so site-install-rb
+site-install-so: install-so
+site-install-rb: install-rb
+
+.SUFFIXES: .c .m .cc .cxx .cpp .C .o
+
+.cc.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) -c $<
+
+.cxx.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) -c $<
+
+.cpp.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) -c $<
+
+.C.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) -c $<
+
+.c.o:
+	$(CC) $(INCFLAGS) $(CPPFLAGS) $(CFLAGS) -c $<
+
+$(DLLIB): $(OBJS) Makefile
+	@-$(RM) $@
+	$(LDSHARED) -o $@ $(OBJS) $(LIBPATH) $(DLDFLAGS) $(LOCAL_LIBS) $(LIBS)
+
+
+
+$(OBJS): ruby.h defines.h

data/ext/langscan/javascript/javascript/extconf.rb

@@ -0,0 +1,3 @@
+require "mkmf"
+dir_config( 'include' )
+create_makefile('langscan/javascript/javascript')

data/ext/langscan/javascript/javascript/javascript.c

@@ -0,0 +1,134 @@
+/* -*- mode: C; indent-tabs-mode: nil; c-basic-offset: 2 c-style: "BSD" -*- */
+/*
+ * _template.c - a template file for LangScan modules
+ * 
+ * Copyright (C) 2004-2005 Akira Tanaka <akr@m17n.org> 
+ *     All rights reserved.
+ *     This is free software with ABSOLUTELY NO WARRANTY.
+ * 
+ * You can redistribute it and/or modify it under the terms of 
+ * the GNU General Public License version 2.
+ */
+
+
+#include <ruby.h>
+#include "javascript.h"
+
+static VALUE token_symbol_list[
+#define LANGSCAN_JAVASCRIPT_TOKEN(token) 1 +
+  1 + LANGSCAN_JAVASCRIPT_TOKEN_LIST 0
+#undef LANGSCAN_JAVASCRIPT_TOKEN
+];
+
+#ifndef RSTRING_PTR
+# define RSTRING_PTR(str) (RSTRING(str)->ptr)
+#endif
+#ifndef RSTRING_LEN
+# define RSTRING_LEN(str) (RSTRING(str)->len)
+#endif
+
+#ifndef RARRAY_PTR
+# define RARRAY_PTR(str) (RARRAY(str)->ptr)
+#endif
+#ifndef RARRAY_LEN
+# define RARRAY_LEN(str) (RARRAY(str)->len)
+#endif
+
+static size_t user_read_str(void **user_data_p, char *buf, size_t maxlen)
+{
+  VALUE user_data = (VALUE)*user_data_p;
+  VALUE user_str = RARRAY_PTR(user_data)[0];
+  VALUE user_off = RARRAY_PTR(user_data)[1];
+  long off = NUM2LONG(user_off);
+  if (RSTRING_LEN(user_str)-off < maxlen) {
+    maxlen = RSTRING_LEN(user_str)-off;
+  }
+  memcpy(buf, RSTRING_PTR(user_str)+off, maxlen);
+  RARRAY_PTR(user_data)[1] = LONG2NUM(off+maxlen);
+  return maxlen;
+}
+
+static void tokenizer_mark(langscan_javascript_tokenizer_t *tokenizer)
+{
+  if (tokenizer == NULL)
+    return;
+  rb_gc_mark((VALUE)langscan_javascript_tokenizer_get_user_data(tokenizer));
+}
+
+static void tokenizer_free(langscan_javascript_tokenizer_t *tokenizer)
+{
+  if (tokenizer == NULL)
+    return;
+  langscan_javascript_free_tokenizer(tokenizer);
+}
+
+static VALUE tokenizer_s_allocate(VALUE klass)
+{
+  return Data_Wrap_Struct(klass, tokenizer_mark, tokenizer_free, NULL);
+}
+
+static VALUE tokenizer_initialize(VALUE self, VALUE user_data)
+{
+  VALUE tmp;
+  user_read_t user_read;
+  langscan_javascript_tokenizer_t *tokenizer;
+  Data_Get_Struct(self, langscan_javascript_tokenizer_t, tokenizer);
+  StringValue(user_data);
+  user_read = user_read_str;
+  user_data = rb_ary_new3(2, rb_str_new4(user_data), INT2FIX(0));
+  RBASIC(user_data)->klass = 0;
+  DATA_PTR(self) = langscan_javascript_make_tokenizer(user_read, (void *)user_data);
+  return self;
+}
+
+static VALUE tokenizer_get_token(VALUE self)
+{
+  langscan_javascript_tokenizer_t *tokenizer;
+  langscan_javascript_token_t token;
+  Data_Get_Struct(self, langscan_javascript_tokenizer_t, tokenizer);
+  if (tokenizer == NULL) { return Qnil; }
+  token = langscan_javascript_get_token(tokenizer);
+  if (token == langscan_javascript_eof) {
+    DATA_PTR(self) = NULL;
+    langscan_javascript_free_tokenizer(tokenizer);
+    return Qnil;
+  }
+  return rb_ary_new3(8,
+    token_symbol_list[token],
+    rb_str_new(langscan_javascript_curtoken_text(tokenizer), langscan_javascript_curtoken_leng(tokenizer)),
+    INT2NUM(langscan_javascript_curtoken_beg_lineno(tokenizer)),
+    INT2NUM(langscan_javascript_curtoken_beg_columnno(tokenizer)),
+    INT2NUM(langscan_javascript_curtoken_beg_byteno(tokenizer)),
+    INT2NUM(langscan_javascript_curtoken_end_lineno(tokenizer)),
+    INT2NUM(langscan_javascript_curtoken_end_columnno(tokenizer)),
+    INT2NUM(langscan_javascript_curtoken_end_byteno(tokenizer)));
+}
+
+static VALUE tokenizer_close(VALUE self)
+{
+  langscan_javascript_tokenizer_t *tokenizer;
+  Data_Get_Struct(self, langscan_javascript_tokenizer_t, tokenizer);
+  if (tokenizer == NULL) { return Qnil; }
+  DATA_PTR(self) = NULL;
+  langscan_javascript_free_tokenizer(tokenizer);
+  return Qnil;
+}
+
+void Init_javascript()
+{
+  VALUE LangScan = rb_define_module("LangScan");
+  VALUE LangScan_JAVASCRIPT = rb_define_module_under(LangScan, "JavaScript");
+  VALUE Tokenizer = rb_define_class_under(LangScan_JAVASCRIPT, "Tokenizer", rb_cData);
+  langscan_javascript_token_t token_id;
+
+  token_id = 0;
+  token_symbol_list[token_id++] = Qnil;
+#define LANGSCAN_JAVASCRIPT_TOKEN(token) token_symbol_list[token_id++] = ID2SYM(rb_intern(#token));
+  LANGSCAN_JAVASCRIPT_TOKEN_LIST
+#undef LANGSCAN_JAVASCRIPT_TOKEN
+
+  rb_define_alloc_func(Tokenizer, tokenizer_s_allocate);
+  rb_define_method(Tokenizer, "initialize", tokenizer_initialize, 1);
+  rb_define_method(Tokenizer, "get_token", tokenizer_get_token, 0);
+  rb_define_method(Tokenizer, "close", tokenizer_close, 0);
+}