bpo-35808: Retire pgen and use pgen2 to generate the parser (GH-11814)

Pgen is the oldest piece of technology in the CPython repository, building it requires various #if[n]def PGEN hacks in other parts of the code and it also depends more and more on CPython internals. This commit removes the old pgen C code and replaces it for a new version implemented in pure Python. This is a modified and adapted version of lib2to3/pgen2 that can generate grammar files compatibles with the current parser.

This commit also eliminates all the #ifdef and code branches related to pgen, simplifying the code and making it more maintainable. The regen-grammar step now uses $(PYTHON_FOR_REGEN) that can be any version of the interpreter, so the new pgen code maintains compatibility with older versions of the interpreter (this also allows regenerating the grammar with the current CI solution that uses Python3.5). The new pgen Python module also makes use of the Grammar/Tokens file that holds the token specification, so is always kept in sync and avoids having to maintain duplicate token definitions.

.gitignore

@@ -73,8 +73,6 @@ PCbuild/arm32/
 PCbuild/obj/
 PCbuild/win32/
 .purify
-Parser/pgen
-Parser/pgen.exe
 __pycache__
 autom4te.cache
 build/

Include/parsetok.h

@@ -12,10 +12,7 @@ extern "C" {
 
 typedef struct {
     int error;
-#ifndef PGEN
-    /* The filename is useless for pgen, see comment in tok_state structure */
     PyObject *filename;
-#endif
     int lineno;
     int offset;
     char *text;                 /* UTF-8-encoded string */

Makefile.pre.in

@@ -290,40 +290,21 @@ LIBFFI_INCLUDEDIR=	@LIBFFI_INCLUDEDIR@
 
 ##########################################################################
 # Parser
-PGEN=		Parser/pgen$(EXE)
-
 POBJS=		\
 		Parser/acceler.o \
 		Parser/grammar1.o \
 		Parser/listnode.o \
 		Parser/node.o \
 		Parser/parser.o \
-		Parser/bitset.o \
-		Parser/metagrammar.o \
-		Parser/firstsets.o \
-		Parser/grammar.o \
 		Parser/token.o \
-		Parser/pgen.o
 
 PARSER_OBJS=	$(POBJS) Parser/myreadline.o Parser/parsetok.o Parser/tokenizer.o
 
-PGOBJS=		\
-		Objects/obmalloc.o \
-		Python/dynamic_annotations.o \
-		Python/mysnprintf.o \
-		Python/pyctype.o \
-		Parser/tokenizer_pgen.o \
-		Parser/printgrammar.o \
-		Parser/parsetok_pgen.o \
-		Parser/pgenmain.o
-
 PARSER_HEADERS= \
 		$(srcdir)/Parser/parser.h \
 		$(srcdir)/Include/parsetok.h \
 		$(srcdir)/Parser/tokenizer.h
 
-PGENOBJS=	$(POBJS) $(PGOBJS)
-
 ##########################################################################
 # Python
 
@@ -802,31 +783,18 @@ Python/sysmodule.o: $(srcdir)/Python/sysmodule.c Makefile
 
 $(IO_OBJS): $(IO_H)
 
-$(PGEN): $(PGENOBJS)
-		$(CC) $(OPT) $(PY_CORE_LDFLAGS) $(PGENOBJS) $(LIBS) -o $(PGEN)
-
 .PHONY: regen-grammar
-regen-grammar: $(PGEN)
+regen-grammar: regen-token
 	# Regenerate Include/graminit.h and Python/graminit.c
 	# from Grammar/Grammar using pgen
 	@$(MKDIR_P) Include
-	$(PGEN) $(srcdir)/Grammar/Grammar \
+	$(PYTHON_FOR_REGEN) -m Parser.pgen $(srcdir)/Grammar/Grammar \
+		$(srcdir)/Grammar/Tokens \
 		$(srcdir)/Include/graminit.h.new \
 		$(srcdir)/Python/graminit.c.new
 	$(UPDATE_FILE) $(srcdir)/Include/graminit.h $(srcdir)/Include/graminit.h.new
 	$(UPDATE_FILE) $(srcdir)/Python/graminit.c $(srcdir)/Python/graminit.c.new
 
-Parser/grammar.o:	$(srcdir)/Parser/grammar.c \
-				$(srcdir)/Include/token.h \
-				$(srcdir)/Include/grammar.h
-Parser/metagrammar.o:	$(srcdir)/Parser/metagrammar.c
-
-Parser/tokenizer_pgen.o:	$(srcdir)/Parser/tokenizer.c
-Parser/parsetok_pgen.o:	$(srcdir)/Parser/parsetok.c
-Parser/printgrammar.o: $(srcdir)/Parser/printgrammar.c
-
-Parser/pgenmain.o:	$(srcdir)/Include/parsetok.h
-
 .PHONY=regen-ast
 regen-ast:
 	# Regenerate Include/Python-ast.h using Parser/asdl_c.py -h
@@ -1016,7 +984,6 @@ PYTHON_HEADERS= \
 		$(srcdir)/Include/longobject.h \
 		$(srcdir)/Include/marshal.h \
 		$(srcdir)/Include/memoryobject.h \
-		$(srcdir)/Include/metagrammar.h \
 		$(srcdir)/Include/methodobject.h \
 		$(srcdir)/Include/modsupport.h \
 		$(srcdir)/Include/moduleobject.h \
@@ -1028,7 +995,6 @@ PYTHON_HEADERS= \
 		$(srcdir)/Include/osdefs.h \
 		$(srcdir)/Include/osmodule.h \
 		$(srcdir)/Include/patchlevel.h \
-		$(srcdir)/Include/pgen.h \
 		$(srcdir)/Include/pgenheaders.h \
 		$(srcdir)/Include/pyarena.h \
 		$(srcdir)/Include/pycapsule.h \
@@ -1771,7 +1737,7 @@ profile-removal:
 	rm -f profile-run-stamp
 
 clobber: clean profile-removal
-	-rm -f $(BUILDPYTHON) $(PGEN) $(LIBRARY) $(LDLIBRARY) $(DLLLIBRARY) \
+	-rm -f $(BUILDPYTHON) $(LIBRARY) $(LDLIBRARY) $(DLLLIBRARY) \
 		tags TAGS \
 		config.cache config.log pyconfig.h Modules/config.c
 	-rm -rf build platform

Misc/NEWS.d/next/Core and Builtins/2019-02-11-00-50-03.bpo-11814.M12CMH.rst

@@ -0,0 +1,2 @@
+Retire pgen and use a modified version of pgen2 to generate the parser.
+Patch by Pablo Galindo.

Misc/coverity_model.c

@@ -92,14 +92,6 @@ wchar_t *Py_DecodeLocale(const char* arg, size_t *size)
    return w;
 }
 
-/* Parser/pgenmain.c */
-grammar *getgrammar(const char *filename)
-{
-    grammar *g;
-    __coverity_tainted_data_sink__(filename);
-    return g;
-}
-
 /* Python/marshal.c */
 
 static Py_ssize_t r_string(char *s, Py_ssize_t n, RFILE *p)

PCbuild/pythoncore.vcxproj

@@ -161,7 +161,6 @@
     <ClInclude Include="..\Include\longobject.h" />
     <ClInclude Include="..\Include\marshal.h" />
     <ClInclude Include="..\Include\memoryobject.h" />
-    <ClInclude Include="..\Include\metagrammar.h" />
     <ClInclude Include="..\Include\methodobject.h" />
     <ClInclude Include="..\Include\modsupport.h" />
     <ClInclude Include="..\Include\moduleobject.h" />
@@ -175,7 +174,6 @@
     <ClInclude Include="..\Include\osmodule.h" />
     <ClInclude Include="..\Include\parsetok.h" />
     <ClInclude Include="..\Include\patchlevel.h" />
-    <ClInclude Include="..\Include\pgen.h" />
     <ClInclude Include="..\Include\pgenheaders.h" />
     <ClInclude Include="..\Include\pyhash.h" />
     <ClInclude Include="..\Include\py_curses.h" />
@@ -372,12 +370,8 @@
     <ClCompile Include="..\Objects\unicodeobject.c" />
     <ClCompile Include="..\Objects\weakrefobject.c" />
     <ClCompile Include="..\Parser\acceler.c" />
-    <ClCompile Include="..\Parser\bitset.c" />
-    <ClCompile Include="..\Parser\firstsets.c" />
-    <ClCompile Include="..\Parser\grammar.c" />
     <ClCompile Include="..\Parser\grammar1.c" />
     <ClCompile Include="..\Parser\listnode.c" />
-    <ClCompile Include="..\Parser\metagrammar.c" />
     <ClCompile Include="..\Parser\myreadline.c" />
     <ClCompile Include="..\Parser\node.c" />
     <ClCompile Include="..\Parser\parser.c" />

PCbuild/pythoncore.vcxproj.filters

@@ -234,9 +234,6 @@
     <ClInclude Include="..\Include\memoryobject.h">
       <Filter>Include</Filter>
     </ClInclude>
-    <ClInclude Include="..\Include\metagrammar.h">
-      <Filter>Include</Filter>
-    </ClInclude>
     <ClInclude Include="..\Include\methodobject.h">
       <Filter>Include</Filter>
     </ClInclude>
@@ -270,9 +267,6 @@
     <ClInclude Include="..\Include\patchlevel.h">
       <Filter>Include</Filter>
     </ClInclude>
-    <ClInclude Include="..\Include\pgen.h">
-      <Filter>Include</Filter>
-    </ClInclude>
     <ClInclude Include="..\Include\pgenheaders.h">
       <Filter>Include</Filter>
     </ClInclude>
@@ -836,24 +830,12 @@
     <ClCompile Include="..\Parser\acceler.c">
       <Filter>Parser</Filter>
     </ClCompile>
-    <ClCompile Include="..\Parser\bitset.c">
-      <Filter>Parser</Filter>
-    </ClCompile>
-    <ClCompile Include="..\Parser\firstsets.c">
-      <Filter>Parser</Filter>
-    </ClCompile>
-    <ClCompile Include="..\Parser\grammar.c">
-      <Filter>Parser</Filter>
-    </ClCompile>
     <ClCompile Include="..\Parser\grammar1.c">
       <Filter>Parser</Filter>
     </ClCompile>
     <ClCompile Include="..\Parser\listnode.c">
       <Filter>Parser</Filter>
     </ClCompile>
-    <ClCompile Include="..\Parser\metagrammar.c">
-      <Filter>Parser</Filter>
-    </ClCompile>
     <ClCompile Include="..\Parser\myreadline.c">
       <Filter>Parser</Filter>
     </ClCompile>