R: Add regular expression R parser

Units/parser-r.r/r-extended.d/expected.tags

@@ -0,0 +1,3 @@
+.First	input.r	/^.First <- function() {$/;"	f
+MASS	input.r	/^  library(MASS)                         # attach a package$/;"	l
+file.path(Sys.getenv("HOME"	input.r	/^  source(file.path(Sys.getenv("HOME"), "R", "mystuff.R"))$/;"	s

Units/parser-r.r/r-extended.d/input.r

@@ -0,0 +1,11 @@
+# From:
+# https://cran.r-project.org/doc/manuals/r-release/R-intro.html#Customizing-the-environment
+.First <- function() {
+  options(prompt="$ ", continue="+\t")  # $ is the prompt
+  options(digits=5, length=999)         # custom numbers and printout
+  x11()                                 # for graphics
+  par(pch = "+")                        # plotting character
+  source(file.path(Sys.getenv("HOME"), "R", "mystuff.R"))
+                                        # my personal functions
+  library(MASS)                         # attach a package
+}

Units/parser-r.r/r-simple.d/expected.tags

@@ -0,0 +1,3 @@
+foo	input.r	/^foo <- function () {$/;"	f
+x	input.r	/^x <- 1$/;"	g
+y	input.r	/^    y <- 2$/;"	v

Units/parser-r.r/r-simple.d/input.r

@@ -0,0 +1,7 @@
+# Copuied from:
+# http://stackoverflow.com/questions/32206608/ctags-and-r-regex
+x <- 1
+foo <- function () {
+    y <- 2
+    return(y)
+}

main/parsers.h

@@ -51,6 +51,7 @@
 	Perl6Parser, \
 	PhpParser, \
 	PythonParser, \
+	RParser, \
 	RexxParser, \
 	RstParser, \
 	RubyParser, \

parsers/r.c

@@ -0,0 +1,215 @@
+/*
+*   Copyright (c) 2003-2004, Ascher Stefan <stievie@utanet.at>
+*
+*   This source code is released for free distribution under the terms of the
+*   GNU General Public License.
+*
+*   This module contains functions for generating tags for R language files.
+*   R is a programming language for statistical computing.
+*   R is GPL Software, get it from http://www.r-project.org/
+*/
+
+/*
+*   INCLUDE FILES
+*/
+#include "general.h"	/* must always come first */
+
+#include <string.h>
+#include <ctype.h>	/* to define isalpha(), isalnum(), isspace() */
+
+#include "debug.h"
+#include "entry.h"
+#include "read.h"
+#include "vstring.h"
+
+#define SKIPSPACE(ch) while (isspace((int)*ch)) \
+  ch++
+
+typedef enum {
+	K_FUNCTION,
+	K_LIBRARY,
+	K_SOURCE,
+	K_GLOBALVAR,
+	K_FUNCVAR,
+	KIND_COUNT
+} rKind;
+
+static kindOption RKinds[KIND_COUNT] = {
+	{TRUE, 'f', "function", "functions"},
+	{TRUE, 'l', "library", "libraries"},
+	{TRUE, 's', "source", "sources"},
+	{TRUE, 'g', "globalVar", "global variables"},
+	{TRUE, 'v', "functionVar", "function variables"},
+};
+
+static void makeRTag (const vString * const name, rKind kind)
+{
+	tagEntryInfo e;
+	initTagEntry (&e, vStringValue (name));
+
+	Assert (kind < KIND_COUNT);
+
+	e.kindName = RKinds[kind].name;
+	e.kind = RKinds[kind].letter;
+
+	makeTagEntry (&e);
+}
+
+static void createRTags (void)
+{
+	vString *vLine = vStringNew ();
+	vString *name = vStringNew ();
+	int ikind;
+	const unsigned char *line;
+
+	while ((line = fileReadLine ()) != NULL)
+	{
+		const unsigned char *cp = (const unsigned char *) line;
+
+		vStringClear (name);
+		while ((*cp != '\0') && (*cp != '#'))
+		{
+			/* iterate to the end of line or to a comment */
+			ikind = -1;
+			switch (*cp)
+			{
+			case 'l':
+			case 's':
+				if (strncasecmp ((const char *) cp, "library", (size_t) 7) == 0)
+				{
+					/* load a library: library(tools) */
+					cp += 7;
+					SKIPSPACE (cp);
+					if (*cp == '(')
+						ikind = K_LIBRARY;
+					else
+						cp -= 7;
+				}
+				else if (strncasecmp ((const char *) cp, "source",
+						(size_t) 6) == 0)
+				{
+					/* load a source file: source("myfile.r") */
+					cp += 6;
+					SKIPSPACE (cp);
+					if (*cp == '(')
+						ikind = K_SOURCE;
+					else
+						cp -= 6;
+				}
+				if (ikind != -1)
+				{
+					cp++;
+
+					vStringClear (name);
+					while ((!isspace ((int) *cp)) && *cp != '\0' && *cp != ')')
+					{
+						vStringPut (name, (int) *cp);
+						cp++;
+					}
+					vStringTerminate (name);
+
+					/* if the string really exists, make a tag of it */
+					if (vStringLength (name) > 0)
+						makeRTag (name, ikind);
+
+					/* prepare for the next iteration */
+					vStringClear (name);
+				}
+				else
+				{
+					vStringPut (name, (int) *cp);
+					cp++;
+				}
+				break;
+			case '<':
+				cp++;
+				if (*cp == '-')
+				{
+					/* assignment: ident <- someval */
+					cp++;
+					SKIPSPACE (cp);
+
+					if (*cp == '\0')
+					{
+						/* not in this line, read next */
+						/* sometimes functions are declared this way:
+						 * ident <-
+						 * function(...)
+						 * {
+						 * ...
+						 * }
+						 * I don't know if there is a reason to write the function keyword
+						 * in a new line
+						 */
+						if ((line = fileReadLine ()) != NULL)
+						{
+							cp = (const unsigned char *) line;
+							SKIPSPACE (cp);
+						}
+					}
+
+					if (strncasecmp ((const char *) cp, "function",
+							(size_t) 8) == 0)
+					{
+						/* it's a function: ident <- function(args) */
+						cp += 8;
+						vStringTerminate (name);
+						/* if the string really exists, make a tag of it */
+						if (vStringLength (name) > 0)
+							makeRTag (name, K_FUNCTION);
+
+						/* prepare for the next iteration */
+						vStringClear (name);
+						break;
+					}
+					else
+					{
+						/* it's a variable: ident <- value */
+						vStringTerminate (name);
+						/* if the string really exists, make a tag of it */
+						if (vStringLength (name) > 0)
+						{
+							if (line[0] == ' ' || line[0] == '\t')
+								makeRTag (name, K_FUNCVAR);
+							else
+								makeRTag (name, K_GLOBALVAR);
+						}
+
+						/* prepare for the next iteration */
+						vStringClear (name);
+						break;
+					}
+				}
+			case ' ':
+			case '\x009':
+				/* skip whitespace */
+				cp++;
+				break;
+			default:
+				/* collect all characters that could be a part of an identifier */
+				vStringPut (name, (int) *cp);
+				cp++;
+				break;
+			}
+		}
+	}
+
+	vStringDelete (name);
+	vStringDelete (vLine);
+}
+
+extern parserDefinition *RParser (void)
+{
+	/* *.r: R files
+	 * *.s;*.q: S files
+	 */
+	static const char *const extensions[] = { "r", "s", "q", NULL };
+	parserDefinition *const def = parserNew ("R");
+	def->extensions = extensions;
+	def->kinds = RKinds;
+	def->kindCount = KIND_COUNT;
+	def->parser = createRTags;
+	return def;
+}
+
+/* vi:set tabstop=4 shiftwidth=4 noexpandtab: */

source.mak

@@ -66,6 +66,7 @@ PARSER_SOURCES =				\
 	$(PARSER_DIR)/perl6.c			\
 	$(PARSER_DIR)/php.c			\
 	$(PARSER_DIR)/python.c			\
+	$(PARSER_DIR)/r.c			\
 	$(PARSER_DIR)/rexx.c			\
 	$(PARSER_DIR)/rst.c			\
 	$(PARSER_DIR)/ruby.c			\

win32/ctags_vs2013.vcxproj

@@ -146,6 +146,7 @@
       <WarningLevel Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">TurnOffAllWarnings</WarningLevel>
     </ClCompile>
     <ClCompile Include="..\parsers\rst.c" />
+    <ClCompile Include="..\parsers\r.c" />
     <ClCompile Include="..\parsers\rexx.c" />
     <ClCompile Include="..\main\routines.c" />
     <ClCompile Include="..\parsers\ruby.c" />

win32/ctags_vs2013.vcxproj.filters

@@ -114,6 +114,9 @@
     <ClCompile Include="..\parsers\python.c">
       <Filter>Source Files\Parsers</Filter>
     </ClCompile>
+    <ClCompile Include="..\parsers\r.c">
+      <Filter>Source Files\Parsers</Filter>
+    </ClCompile>
     <ClCompile Include="..\parsers\rexx.c">
       <Filter>Source Files\Parsers</Filter>
     </ClCompile>