Move keywords.c/kwlookup.c into src/common/.

Now that we have src/common/ for code shared between frontend and backend,
we can get rid of (most of) the klugy ways that the keyword table and
keyword lookup code were formerly shared between different uses.
This is a first step towards a more general plan of getting rid of
special-purpose kluges for sharing code in src/bin/.

I chose to merge kwlookup.c back into keywords.c, as it once was, and
always has been so far as keywords.h is concerned.  We could have
kept them separate, but there is noplace that uses ScanKeywordLookup
without also wanting access to the backend's keyword list, so there
seems little point.

ecpg is still a bit weird, but at least now the trickiness is documented.

I think that the MSVC build script should require no adjustments beyond
what's done here ... but we'll soon find out.

src/common/Makefile

@@ -36,8 +36,9 @@ override CPPFLAGS += -DVAL_LDFLAGS_EX="\"$(LDFLAGS_EX)\""
 override CPPFLAGS += -DVAL_LDFLAGS_SL="\"$(LDFLAGS_SL)\""
 override CPPFLAGS += -DVAL_LIBS="\"$(LIBS)\""
 
-OBJS_COMMON = config_info.o controldata_utils.o exec.o pg_lzcompress.o \
-	pgfnames.o psprintf.o relpath.o rmtree.o string.o username.o wait_error.o
+OBJS_COMMON = config_info.o controldata_utils.o exec.o keywords.o \
+	pg_lzcompress.o pgfnames.o psprintf.o relpath.o rmtree.o \
+	string.o username.o wait_error.o
 
 OBJS_FRONTEND = $(OBJS_COMMON) fe_memutils.o restricted_token.o
 
@@ -83,5 +84,14 @@ $(OBJS_SRV): | submake-errcodes
 submake-errcodes:
 	$(MAKE) -C ../backend submake-errcodes
 
+# Dependencies of keywords.o need to be managed explicitly to make sure
+# that you don't get broken parsing code, even in a non-enable-depend build.
+# Note that gram.h isn't required for the frontend version of keywords.o.
+$(top_builddir)/src/include/parser/gram.h: $(top_srcdir)/src/backend/parser/gram.y
+	$(MAKE) -C $(top_builddir)/src/backend $(top_builddir)/src/include/parser/gram.h
+
+keywords.o: $(top_srcdir)/src/include/parser/kwlist.h
+keywords_srv.o: $(top_builddir)/src/include/parser/gram.h $(top_srcdir)/src/include/parser/kwlist.h
+
 clean distclean maintainer-clean:
 	rm -f libpgcommon.a libpgcommon_srv.a $(OBJS_FRONTEND) $(OBJS_SRV)

src/common/keywords.c

@@ -0,0 +1,114 @@
+/*-------------------------------------------------------------------------
+ *
+ * keywords.c
+ *	  lexical token lookup for key words in PostgreSQL
+ *
+ *
+ * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  src/common/keywords.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef FRONTEND
+#include "postgres.h"
+#else
+#include "postgres_fe.h"
+#endif
+
+#ifndef FRONTEND
+
+#include "parser/gramparse.h"
+
+#define PG_KEYWORD(a,b,c) {a,b,c},
+
+#else
+
+#include "common/keywords.h"
+
+/*
+ * We don't need the token number for frontend uses, so leave it out to avoid
+ * requiring backend headers that won't compile cleanly here.
+ */
+#define PG_KEYWORD(a,b,c) {a,0,c},
+
+#endif   /* FRONTEND */
+
+
+const ScanKeyword ScanKeywords[] = {
+#include "parser/kwlist.h"
+};
+
+const int	NumScanKeywords = lengthof(ScanKeywords);
+
+
+/*
+ * ScanKeywordLookup - see if a given word is a keyword
+ *
+ * The table to be searched is passed explicitly, so that this can be used
+ * to search keyword lists other than the standard list appearing above.
+ *
+ * Returns a pointer to the ScanKeyword table entry, or NULL if no match.
+ *
+ * The match is done case-insensitively.  Note that we deliberately use a
+ * dumbed-down case conversion that will only translate 'A'-'Z' into 'a'-'z',
+ * even if we are in a locale where tolower() would produce more or different
+ * translations.  This is to conform to the SQL99 spec, which says that
+ * keywords are to be matched in this way even though non-keyword identifiers
+ * receive a different case-normalization mapping.
+ */
+const ScanKeyword *
+ScanKeywordLookup(const char *text,
+				  const ScanKeyword *keywords,
+				  int num_keywords)
+{
+	int			len,
+				i;
+	char		word[NAMEDATALEN];
+	const ScanKeyword *low;
+	const ScanKeyword *high;
+
+	len = strlen(text);
+	/* We assume all keywords are shorter than NAMEDATALEN. */
+	if (len >= NAMEDATALEN)
+		return NULL;
+
+	/*
+	 * Apply an ASCII-only downcasing.  We must not use tolower() since it may
+	 * produce the wrong translation in some locales (eg, Turkish).
+	 */
+	for (i = 0; i < len; i++)
+	{
+		char		ch = text[i];
+
+		if (ch >= 'A' && ch <= 'Z')
+			ch += 'a' - 'A';
+		word[i] = ch;
+	}
+	word[len] = '\0';
+
+	/*
+	 * Now do a binary search using plain strcmp() comparison.
+	 */
+	low = keywords;
+	high = keywords + (num_keywords - 1);
+	while (low <= high)
+	{
+		const ScanKeyword *middle;
+		int			difference;
+
+		middle = low + (high - low) / 2;
+		difference = strcmp(middle->name, word);
+		if (difference == 0)
+			return middle;
+		else if (difference < 0)
+			low = middle + 1;
+		else
+			high = middle - 1;
+	}
+
+	return NULL;
+}