1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408
|
/*
* $Id: ruby.c 571 2007-06-24 23:32:14Z elliotth $
*
* Copyright (c) 2000-2001, Thaddeus Covert <sahuagin@mediaone.net>
* Copyright (c) 2002 Matthias Veit <matthias_veit@yahoo.de>
* Copyright (c) 2004 Elliott Hughes <enh@acm.org>
*
* 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 Ruby language
* files.
*/
/*
* INCLUDE FILES
*/
#include "general.h" /* must always come first */
#include <string.h>
#include "entry.h"
#include "parse.h"
#include "read.h"
#include "vstring.h"
/*
* DATA DECLARATIONS
*/
typedef enum {
K_UNDEFINED = -1, K_CLASS, K_METHOD, K_MODULE, K_SINGLETON
} rubyKind;
/*
* DATA DEFINITIONS
*/
static kindOption RubyKinds [] = {
{ TRUE, 'c', "class", "classes" },
{ TRUE, 'f', "method", "methods" },
{ TRUE, 'm', "module", "modules" },
{ TRUE, 'F', "singleton method", "singleton methods" }
};
static stringList* nesting = 0;
/*
* FUNCTION DEFINITIONS
*/
/*
* Returns a string describing the scope in 'list'.
* We record the current scope as a list of entered scopes.
* Scopes corresponding to 'if' statements and the like are
* represented by empty strings. Scopes corresponding to
* modules and classes are represented by the name of the
* module or class.
*/
static vString* stringListToScope (const stringList* list)
{
unsigned int i;
unsigned int chunks_output = 0;
vString* result = vStringNew ();
const unsigned int max = stringListCount (list);
for (i = 0; i < max; ++i)
{
vString* chunk = stringListItem (list, i);
if (vStringLength (chunk) > 0)
{
vStringCatS (result, (chunks_output++ > 0) ? "." : "");
vStringCatS (result, vStringValue (chunk));
}
}
return result;
}
/*
* Attempts to advance 's' past 'literal'.
* Returns TRUE if it did, FALSE (and leaves 's' where
* it was) otherwise.
*/
static boolean canMatch (const unsigned char** s, const char* literal)
{
const int literal_length = strlen (literal);
const unsigned char next_char = *(*s + literal_length);
if (strncmp ((const char*) *s, literal, literal_length) != 0)
{
return FALSE;
}
/* Additionally check that we're at the end of a token. */
if ( ! (next_char == 0 || isspace (next_char) || next_char == '('))
{
return FALSE;
}
*s += literal_length;
return TRUE;
}
/*
* Attempts to advance 'cp' past a Ruby operator method name. Returns
* TRUE if successful (and copies the name into 'name'), FALSE otherwise.
*/
static boolean parseRubyOperator (vString* name, const unsigned char** cp)
{
static const char* RUBY_OPERATORS[] = {
"[]", "[]=",
"**",
"!", "~", "+@", "-@",
"*", "/", "%",
"+", "-",
">>", "<<",
"&",
"^", "|",
"<=", "<", ">", ">=",
"<=>", "==", "===", "!=", "=~", "!~",
"`",
0
};
int i;
for (i = 0; RUBY_OPERATORS[i] != 0; ++i)
{
if (canMatch (cp, RUBY_OPERATORS[i]))
{
vStringCatS (name, RUBY_OPERATORS[i]);
return TRUE;
}
}
return FALSE;
}
/*
* Emits a tag for the given 'name' of kind 'kind' at the current nesting.
*/
static void emitRubyTag (vString* name, rubyKind kind)
{
tagEntryInfo tag;
vString* scope;
vStringTerminate (name);
scope = stringListToScope (nesting);
initTagEntry (&tag, vStringValue (name));
if (vStringLength (scope) > 0) {
tag.extensionFields.scope [0] = "class";
tag.extensionFields.scope [1] = vStringValue (scope);
}
tag.kindName = RubyKinds [kind].name;
tag.kind = RubyKinds [kind].letter;
makeTagEntry (&tag);
stringListAdd (nesting, vStringNewCopy (name));
vStringClear (name);
vStringDelete (scope);
}
/* Tests whether 'ch' is a character in 'list'. */
static boolean charIsIn (char ch, const char* list)
{
return (strchr (list, ch) != 0);
}
/* Advances 'cp' over leading whitespace. */
static void skipWhitespace (const unsigned char** cp)
{
while (isspace (**cp))
{
++*cp;
}
}
/*
* Copies the characters forming an identifier from *cp into
* name, leaving *cp pointing to the character after the identifier.
*/
static rubyKind parseIdentifier (
const unsigned char** cp, vString* name, rubyKind kind)
{
/* Method names are slightly different to class and variable names.
* A method name may optionally end with a question mark, exclamation
* point or equals sign. These are all part of the name.
* A method name may also contain a period if it's a singleton method.
*/
const char* also_ok = (kind == K_METHOD) ? "_.?!=" : "_";
skipWhitespace (cp);
/* Check for an anonymous (singleton) class such as "class << HTTP". */
if (kind == K_CLASS && **cp == '<' && *(*cp + 1) == '<')
{
return K_UNDEFINED;
}
/* Check for operators such as "def []=(key, val)". */
if (kind == K_METHOD || kind == K_SINGLETON)
{
if (parseRubyOperator (name, cp))
{
return kind;
}
}
/* Copy the identifier into 'name'. */
while (**cp != 0 && (isalnum (**cp) || charIsIn (**cp, also_ok)))
{
char last_char = **cp;
vStringPut (name, last_char);
++*cp;
if (kind == K_METHOD)
{
/* Recognize singleton methods. */
if (last_char == '.')
{
vStringTerminate (name);
vStringClear (name);
return parseIdentifier (cp, name, K_SINGLETON);
}
/* Recognize characters which mark the end of a method name. */
if (charIsIn (last_char, "?!="))
{
break;
}
}
}
return kind;
}
static void readAndEmitTag (const unsigned char** cp, rubyKind expected_kind)
{
if (isspace (**cp))
{
vString *name = vStringNew ();
rubyKind actual_kind = parseIdentifier (cp, name, expected_kind);
if (actual_kind == K_UNDEFINED || vStringLength (name) == 0)
{
/*
* What kind of tags should we create for code like this?
*
* %w(self.clfloor clfloor).each do |name|
* module_eval <<-"end;"
* def #{name}(x, y=1)
* q, r = x.divmod(y)
* q = q.to_i
* return q, r
* end
* end;
* end
*
* Or this?
*
* class << HTTP
*
* For now, we don't create any.
*/
}
else
{
emitRubyTag (name, actual_kind);
}
vStringDelete (name);
}
}
static void enterUnnamedScope (void)
{
stringListAdd (nesting, vStringNewInit (""));
}
static void findRubyTags (void)
{
const unsigned char *line;
boolean inMultiLineComment = FALSE;
nesting = stringListNew ();
/* FIXME: this whole scheme is wrong, because Ruby isn't line-based.
* You could perfectly well write:
*
* def
* method
* puts("hello")
* end
*
* if you wished, and this function would fail to recognize anything.
*/
while ((line = fileReadLine ()) != NULL)
{
const unsigned char *cp = line;
if (canMatch (&cp, "=begin"))
{
inMultiLineComment = TRUE;
continue;
}
if (canMatch (&cp, "=end"))
{
inMultiLineComment = FALSE;
continue;
}
skipWhitespace (&cp);
/* Avoid mistakenly starting a scope for modifiers such as
*
* return if <exp>
*
* FIXME: this is fooled by code such as
*
* result = if <exp>
* <a>
* else
* <b>
* end
*
* FIXME: we're also fooled if someone does something heinous such as
*
* puts("hello") \
* unless <exp>
*/
if (canMatch (&cp, "case") || canMatch (&cp, "for") ||
canMatch (&cp, "if") || canMatch (&cp, "unless") ||
canMatch (&cp, "while"))
{
enterUnnamedScope ();
}
/*
* "module M", "class C" and "def m" should only be at the beginning
* of a line.
*/
if (canMatch (&cp, "module"))
{
readAndEmitTag (&cp, K_MODULE);
}
else if (canMatch (&cp, "class"))
{
readAndEmitTag (&cp, K_CLASS);
}
else if (canMatch (&cp, "def"))
{
readAndEmitTag (&cp, K_METHOD);
}
while (*cp != '\0')
{
/* FIXME: we don't cope with here documents,
* or regular expression literals, or ... you get the idea.
* Hopefully, the restriction above that insists on seeing
* definitions at the starts of lines should keep us out of
* mischief.
*/
if (inMultiLineComment || isspace (*cp))
{
++cp;
}
else if (*cp == '#')
{
/* FIXME: this is wrong, but there *probably* won't be a
* definition after an interpolated string (where # doesn't
* mean 'comment').
*/
break;
}
else if (canMatch (&cp, "begin") || canMatch (&cp, "do"))
{
enterUnnamedScope ();
}
else if (canMatch (&cp, "end") && stringListCount (nesting) > 0)
{
/* Leave the most recent scope. */
vStringDelete (stringListLast (nesting));
stringListRemoveLast (nesting);
}
else if (*cp == '"')
{
/* Skip string literals.
* FIXME: should cope with escapes and interpolation.
*/
do {
++cp;
} while (*cp != 0 && *cp != '"');
}
else if (*cp != '\0')
{
do
++cp;
while (isalnum (*cp) || *cp == '_');
}
}
}
stringListDelete (nesting);
}
extern parserDefinition* RubyParser (void)
{
static const char *const extensions [] = { "rb", "ruby", NULL };
parserDefinition* def = parserNew ("Ruby");
def->kinds = RubyKinds;
def->kindCount = KIND_COUNT (RubyKinds);
def->extensions = extensions;
def->parser = findRubyTags;
return def;
}
/* vi:set tabstop=4 shiftwidth=4: */
|