docs/manual/cocci_syntax.tex

   1
   2 %\section{The SmPL Grammar}
   3
   4 % This section presents the SmPL grammar.  This definition follows closely
   5 % our implementation using the Menhir parser generator \cite{menhir}.
   6
   7 This document presents the grammar of the SmPL language used by the
   8 \href{http://coccinelle.lip6.fr/}{Coccinelle tool}.  For the most
   9 part, the grammar is written using standard notation.  In some rules,
  10 however, the left-hand side is in all uppercase letters.  These are
  11 macros, which take one or more grammar rule right-hand-sides as
  12 arguments.  The grammar also uses some unspecified nonterminals, such
  13 as \T{id}, \T{const}, etc.  These refer to the sets suggested by
  14 the name, {\em i.e.}, \T{id} refers to the set of possible
  15 C-language identifiers, while \T{const} refers to the set of
  16 possible C-language constants.
  17 %
  18 \ifhevea
  19 A PDF version of this documentation is available at
  20 \url{http://coccinelle.lip6.fr/docs/main_grammar.pdf}.
  21 \else
  22 A HTML version of this documentation is available online at
  23 \url{http://coccinelle.lip6.fr/docs/main_grammar.html}.
  24 \fi
  25
  26 \section{Program}
  27
  28 \begin{grammar}
  29   \RULE{\rt{program}}
  30   \CASE{\any{\NT{include\_cocci}} \some{\NT{changeset}}}
  31
  32   \RULE{\rt{include\_cocci}}
  33   \CASE{using \NT{string}}
  34   \CASE{using \NT{pathToIsoFile}}
  35   \CASE{virtual \T{id} \ANY{, \T{id}}}
  36
  37   \RULE{\rt{changeset}}
  38   \CASE{\NT{metavariables} \NT{transformation}}
  39   \CASE{\NT{script\_metavariables} \T{script\_code}}
  40 %  \CASE{\NT{metavariables} \ANY{--- filename +++ filename} \NT{transformation}}
  41 \end{grammar}
  42
  43 \noindent
  44 \T{script\_code} is any code in the chosen scripting language.  Parsing of
  45 the semantic patch does not check the validity of this code; any errors are
  46 first detected when the code is executed.  Furthermore, \texttt{@} should
  47 not be use in this code.  Spatch scans the script code for the next
  48 \texttt{@} and considers that to be the beginning of the next rule, even if
  49 \texttt{@} occurs within e.g., a string or a comment.
  50
  51 \texttt{virtual} keyword is used to declare virtual rules. Virtual
  52 rules may be subsequently used as a dependency for the rules in the
  53 SmPL file. Whether a virtual rule is defined or not is controlled by
  54 the \texttt{-D} option on the command line.
  55
  56 % Between the metavariables and the transformation rule, there can be a
  57 % specification of constraints on the names of the old and new files,
  58 % analogous to the filename specifications in the standard patch syntax.
  59 % (see Figure \ref{scsiglue_patch}).
  60
  61 \section{Metavariables for transformations}
  62
  63 The \NT{rulename} portion of the metavariable declaration can specify
  64 properties of a rule such as its name, the names of the rules that it
  65 depends on, the isomorphisms to be used in processing the rule, and whether
  66 quantification over paths should be universal or existential.  The optional
  67 annotation {\tt expression} indicates that the pattern is to be considered
  68 as matching an expression, and thus can be used to avoid some parsing
  69 problems.
  70
  71 The \NT{metadecl} portion of the metavariable declaration defines various
  72 types of metavariables that will be used for matching in the transformation
  73 section.
  74
  75 \begin{grammar}
  76   \RULE{\rt{metavariables}}
  77   \CASE{@@ \any{\NT{metadecl}} @@}
  78   \CASE{@ \NT{rulename} @ \any{\NT{metadecl}} @@}
  79
  80   \RULE{\rt{rulename}}
  81   \CASE{\T{id} \OPT{extends \T{id}} \OPT{depends on \NT{dep}} \opt{\NT{iso}}
  82     \opt{\NT{disable-iso}} \opt{\NT{exists}} \opt{expression}}
  83
  84   \RULE{\rt{dep}}
  85   \CASE{\NT{pnrule}}
  86   \CASE{\NT{dep} \&\& \NT{dep}}
  87   \CASE{\NT{dep} || \NT{dep}}
  88
  89   \RULE{\rt{pnrule}}
  90   \CASE{\T{id}}
  91   \CASE{!\T{id}}
  92   \CASE{ever \T{id}}
  93   \CASE{never \T{id}}
  94   \CASE{(\NT{dep})}
  95
  96   \RULE{\rt{iso}}
  97   \CASE{using \NT{string} \ANY{, \NT{string}}}
  98
  99   \RULE{\rt{disable-iso}}
 100   \CASE{disable \NT{COMMA\_LIST}\mth{(}\T{id}\mth{)}}
 101
 102   \RULE{\rt{exists}}
 103   \CASE{exists}
 104   \CASE{forall}
 105 %  \CASE{\opt{reverse} forall}
 106
 107   \RULE{\rt{COMMA\_LIST}\mth{(}\rt{elem}\mth{)}}
 108   \CASE{\NT{elem} \ANY{, \NT{elem}}}
 109 \end{grammar}
 110
 111 The keyword \KW{disable} is normally used with the names of
 112 isomorphisms defined in standard.iso or whatever isomorphism file has been
 113 included.  There are, however, some other isomorphisms that are built into
 114 the implementation of Coccinelle and that can be disabled as well.  Their
 115 names are given below.  In each case, the text descibes the standard
 116 behavior.  Using \NT{disable-iso} with the given name disables this behavior.
 117
 118 \begin{itemize}
 119 \item \KW{optional\_storage}: A SmPL function definition that does not
 120   specify any visibility (i.e., static or extern), or a SmPL variable
 121   declaration that does not specify any storage (i.e., auto, static,
 122   register, or extern), matches a function declaration or variable
 123   declaration with any visibility or storage, respectively.
 124 \item \KW{optional\_qualifier}: This is similar to \KW{optional\_storage},
 125   except that here is it the qualifier (i.e., const or volatile) that does
 126   not have to be specified in the SmPL code, but may be present in the C code.
 127 \item \KW{value\_format}: Integers in various formats, e.g., 1 and 0x1, are
 128   considered to be equivalent in the matching process.
 129 \item \KW{comm\_assoc}: An expression of the form \NT{exp} \NT{bin\_op}
 130   \KW{...}, where \NT{bin\_op} is commutative and associative, is
 131   considered to match any top-level sequence of \NT{bin\_op} operators
 132   containing \NT{exp} as the top-level argument.
 133 \end{itemize}
 134
 135 The possible types of metavariable declarations are defined by the grammar
 136 rule below.  Metavariables should occur at least once in the transformation
 137 immediately following their declaration.  Fresh metavariables must only be
 138 used in {\tt +} code.  These properties are not expressed in the grammar,
 139 but are checked by a subsequent analysis.  The metavariables are designated
 140 according to the kind of terms they can match, such as a statement, an
 141 identifier, or an expression.  An expression metavariable can be further
 142 constrained by its type.
 143
 144 \begin{grammar}
 145   \RULE{\rt{metadecl}}
 146   \CASE{fresh identifier \NT{ids} ;}
 147   \CASE{identifier \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_regexp}\mth{)} ;}
 148   \CASE{identifier \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_virt\_or\_not\_eq}\mth{)} ;}
 149   \CASE{parameter \opt{list} \NT{ids} ;}
 150   \CASE{parameter list [ \NT{id} ] \NT{ids} ;}
 151   \CASE{type \NT{ids} ;}
 152   \CASE{statement \opt{list} \NT{ids} ;}
 153   \CASE{typedef \NT{ids} ;}
 154   \CASE{declarer name \NT{ids} ;}
 155 %  \CASE{\opt{local} function \NT{pmid\_with\_not\_eq\_list} ;}
 156   \CASE{declarer \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_regexp}\mth{)} ;}
 157   \CASE{declarer \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 158   \CASE{iterator name \NT{ids} ;}
 159   \CASE{iterator \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_regexp}\mth{)} ;}
 160   \CASE{iterator \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 161 %  \CASE{error \NT{pmid\_with\_not\_eq\_list} ; }
 162   \CASE{\opt{local} idexpression \opt{\NT{ctype}} \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 163   \CASE{\opt{local} idexpression \OPT{\ttlb \NT{ctypes}\ttrb~\any{*}} \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 164   \CASE{\opt{local} idexpression \some{*} \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 165   \CASE{expression list \NT{ids} ;}
 166   \CASE{expression \some{*} \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 167   \CASE{expression \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_ceq}\mth{)} ;}
 168   \CASE{expression list [ ident ] \NT{ids} ;}
 169   \CASE{\NT{ctype} [ ] \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 170   \CASE{\NT{ctype} \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_ceq}\mth{)} ;}
 171   \CASE{\ttlb \NT{ctypes}\ttrb~\any{*} \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_ceq}\mth{)} ;}
 172   \CASE{\ttlb \NT{ctypes}\ttrb~\any{*} [ ] \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 173   \CASE{constant \opt{\NT{ctype}} \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 174   \CASE{constant \OPT{\ttlb \NT{ctypes}\ttrb~\any{*}} \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq}\mth{)} ;}
 175   \CASE{position \opt{any} \NT{COMMA\_LIST}\mth{(}\NT{pmid\_with\_not\_eq\_mid}\mth{)} ;}
 176 \end{grammar}
 177
 178 \begin{grammar}
 179   \RULE{\rt{ids}}
 180   \CASE{\NT{COMMA\_LIST}\mth{(}\NT{pmid}\mth{)}}
 181
 182   \RULE{\rt{pmid}}
 183   \CASE{\T{id}}
 184   \CASE{\NT{mid}}
 185 %   \CASE{list}
 186 %   \CASE{error}
 187 %   \CASE{type}
 188
 189   \RULE{\rt{mid}}  \CASE{\T{rulename\_id}.\T{id}}
 190
 191   \RULE{\rt{pmid\_with\_regexp}}
 192   \CASE{\NT{pmid} \~{}= \NT{regexp}}
 193
 194   \RULE{\rt{pmid\_with\_not\_eq}}
 195   \CASE{\NT{pmid} \OPT{!= \NT{id\_or\_meta}}}
 196   \CASE{\NT{pmid}
 197      \OPT{!= \ttlb~\NT{COMMA\_LIST}\mth{(}\NT{id\_or\_meta}\mth{)} \ttrb}}
 198
 199   \RULE{\rt{pmid\_with\_virt\_or\_not\_eq}}
 200   \CASE{virtual.\T{id}}
 201   \CASE{\NT{pmid\_with\_not\_eq}}
 202
 203   \RULE{\rt{pmid\_with\_not\_ceq}}
 204   \CASE{\NT{pmid} \OPT{!= \NT{id\_or\_cst}}}
 205   \CASE{\NT{pmid} \OPT{!= \ttlb~\NT{COMMA\_LIST}\mth{(}\NT{id\_or\_cst}\mth{)} \ttrb}}
 206
 207   \RULE{\rt{id\_or\_cst}}
 208   \CASE{\T{id}}
 209   \CASE{\T{integer}}
 210
 211   \RULE{\rt{id\_or\_meta}}
 212   \CASE{\T{id}}
 213   \CASE{\T{rulename\_id}.\T{id}}
 214
 215   \RULE{\rt{pmid\_with\_not\_eq\_mid}}
 216   \CASE{\NT{pmid} \OPT{!= \NT{mid}}}
 217   \CASE{\NT{pmid} \OPT{!= \ttlb~\NT{COMMA\_LIST}\mth{(}\NT{mid}\mth{)} \ttrb}}
 218 \end{grammar}
 219
 220 Subsequently, we refer to arbitrary metavariables as
 221 \mth{\msf{metaid}^{\mbox{\scriptsize{\it{ty}}}}}, where {\it{ty}}
 222 indicates the {\it metakind} used in the declaration of the variable.
 223 For example, \mth{\msf{metaid}^{\ssf{Type}}} refers to a metavariable
 224 that was declared using \texttt{type} and stands for any type.
 225
 226 The \NT{ctype} and \NT{ctypes} nonterminals are used by both the grammar of
 227 metavariable declarations and the grammar of transformations, and are
 228 defined on page~\pageref{types}.
 229
 230 An identifier metavariable with {\tt virtual} as its ``rule name'' is given
 231 a value on the command line.  For example, if a semantic patch contains a
 232 rule that declares an identifier metavariable with the name {\tt
 233   virtual.alloc}, then the command line could contain {\tt -D
 234   alloc=kmalloc}.  There should not be space around the {\tt =}.  An
 235 example is in {\tt demos/vm.cocci} and {\tt demos/vm.c}.
 236
 237 \section{Metavariables for scripts}
 238
 239 Metavariables for scripts can only be inherited from transformation rules.
 240 In the spirit of scripting languages such as Python that use dynamic
 241 typing, metavariables for scripts do not include type declarations.
 242
 243 \begin{grammar}
 244   \RULE{\rt{script\_metavariables}}
 245   \CASE{@ script:\NT{language} \OPT{depends on \NT{dep}} @
 246         \any{\NT{script\_metadecl}} @@}
 247   \CASE{@ initialize:\NT{language} \OPT{depends on \NT{dep}} @}
 248   \CASE{@ finalize:\NT{language} \OPT{depends on \NT{dep}} @}
 249
 250   \RULE{\rt{language}} \CASE{python}
 251
 252   \RULE{\rt{script\_metadecl}} \CASE{\T{id} <{}< \T{rulename\_id}.\T{id} ;}
 253 \end{grammar}
 254
 255 Currently, the only scripting language that is supported is Python.  The
 256 set of available scripting languages may be extended at some point.
 257
 258 Script rules declared with \KW{initialize} are run before the treatment of
 259 any file.  Script rules declared with \KW{finalize} are run when the
 260 treatment of all of the files has completed.  There can be at most one of
 261 each per scripting language (thus currently at most one of each).
 262 Initialize and finalize script rules do not have access to SmPL
 263 metavariables.  Nevertheless, a finalize script rule can access any
 264 variables initialized by the other script rules, allowing information to be
 265 transmitted from the matching process to the finalize rule.
 266
 267 \section{Transformation}
 268
 269 The transformation specification essentially has the form of C code,
 270 except that lines to remove are annotated with \verb+-+ in the first
 271 column, and lines to add are annotated with \verb-+-.  A
 272 transformation specification can also use {\em dots}, ``\verb-...-'',
 273 describing an arbitrary sequence of function arguments or instructions
 274 within a control-flow path.  Dots may be modified with a {\tt when}
 275 clause, indicating a pattern that should not occur anywhere within the
 276 matched sequence.  Finally, a transformation can specify a disjunction
 277 of patterns, of the form \mtt{( \mth{\mita{pat}_1} | \mita{\ldots} |
 278   \mth{\mita{pat}_n} )} where each \texttt{(}, \texttt{|} or
 279 \texttt{)} is in column 0 or preceded by \texttt{\textbackslash}.
 280
 281 The grammar that we present for the transformation is not actually the
 282 grammar of the SmPL code that can be written by the programmer, but is
 283 instead the grammar of the slice of this consisting of the {\tt -}
 284 annotated and the unannotated code (the context of the transformed lines),
 285 or the {\tt +} annotated code and the unannotated code.  For example, for
 286 parsing purposes, the following transformation
 287 %presented in Section \ref{sec:seq2}
 288 is split into the two variants shown below and each is parsed
 289 separately.
 290
 291 \begin{center}
 292 \begin{tabular}{c}
 293 \begin{lstlisting}[language=Cocci]
 294   proc_info_func(...) {
 295     <...
 296 @--    hostno
 297 @++    hostptr->host_no
 298     ...>
 299  }
 300 \end{lstlisting}\\
 301 \end{tabular}
 302 \end{center}
 303
 304 {%\sizecodebis
 305 \begin{center}
 306 \begin{tabular}{p{5cm}p{3cm}p{5cm}}
 307 \begin{lstlisting}[language=Cocci]
 308   proc_info_func(...) {
 309     <...
 310 @--    hostno
 311     ...>
 312  }
 313 \end{lstlisting}
 314 &&
 315 \begin{lstlisting}[language=Cocci]
 316   proc_info_func(...) {
 317     <...
 318 @++    hostptr->host_no
 319     ...>
 320  }
 321 \end{lstlisting}
 322 \end{tabular}
 323 \end{center}
 324 }
 325
 326 \noindent
 327 Requiring that both slices parse correctly ensures that the rule matches
 328 syntactically valid C code and that it produces syntactically valid C code.
 329 The generated parse trees are then merged for use in the subsequent
 330 matching and transformation process.
 331
 332 The grammar for the minus or plus slice of a transformation is as follows:
 333
 334 \begin{grammar}
 335
 336   \RULE{\rt{transformation}}
 337   \CASE{\some{\NT{include}}}
 338   \CASE{\NT{OPTDOTSEQ}\mth{(}\NT{expr}, \NT{when}\mth{)}}
 339   \CASE{\NT{OPTDOTSEQ}\mth{(}\some{\NT{decl\_stmt}}, \NT{when}\mth{)}}
 340   \CASE{\NT{OPTDOTSEQ}\mth{(}\NT{fundecl}, \NT{when}\mth{)}}
 341
 342   \RULE{\rt{include}}
 343   \CASE{\#include \T{include\_string}}
 344
 345 %  \RULE{\rt{fun\_decl\_stmt}}
 346 %  \CASE{\NT{decl\_stmt}}
 347 %  \CASE{\NT{fundecl}}
 348
 349 %  \CASE{\NT{ctype}}
 350 %  \CASE{\ttlb \NT{initialize\_list} \ttrb}
 351 %  \CASE{\NT{toplevel\_seq\_start\_after\_dots\_init}}
 352 %
 353 %  \RULE{\rt{toplevel\_seq\_start\_after\_dots\_init}}
 354 %  \CASE{\NT{stmt\_dots} \NT{toplevel\_after\_dots}}
 355 %  \CASE{\NT{expr} \opt{\NT{toplevel\_after\_exp}}}
 356 %  \CASE{\NT{decl\_stmt\_expr} \opt{\NT{toplevel\_after\_stmt}}}
 357 %
 358 %  \RULE{\rt{stmt\_dots}}
 359 %  \CASE{... \any{\NT{when}}}
 360 %  \CASE{<... \any{\NT{when}} \NT{nest\_after\_dots} ...>}
 361 %  \CASE{<+... \any{\NT{when}} \NT{nest\_after\_dots} ...+>}
 362
 363   \RULE{\rt{when}}
 364   \CASE{when != \NT{when\_code}}
 365   \CASE{when = \NT{rule\_elem\_stmt}}
 366   \CASE{when \NT{COMMA\_LIST}\mth{(}\NT{any\_strict}\mth{)}}
 367   \CASE{when true != \NT{expr}}
 368   \CASE{when false != \NT{expr}}
 369
 370   \RULE{\rt{when\_code}}
 371   \CASE{\NT{OPTDOTSEQ}\mth{(}\some{\NT{decl\_stmt}}, \NT{when}\mth{)}}
 372   \CASE{\NT{OPTDOTSEQ}\mth{(}\NT{expr}, \NT{when}\mth{)}}
 373
 374   \RULE{\rt{rule\_elem\_stmt}}
 375   \CASE{\NT{one\_decl}}
 376   \CASE{\NT{expr};}
 377   \CASE{return \opt{\NT{expr}};}
 378   \CASE{break;}
 379   \CASE{continue;}
 380   \CASE{\bs(\NT{rule\_elem\_stmt} \SOME{\bs| \NT{rule\_elem\_stmt}}\bs)}
 381
 382   \RULE{\rt{any\_strict}}
 383   \CASE{any}
 384   \CASE{strict}
 385   \CASE{forall}
 386   \CASE{exists}
 387
 388 %  \RULE{\rt{nest\_after\_dots}}
 389 %  \CASE{\NT{decl\_stmt\_exp} \opt{\NT{nest\_after\_stmt}}}
 390 %  \CASE{\opt{\NT{exp}} \opt{\NT{nest\_after\_exp}}}
 391 %
 392 %  \RULE{\rt{nest\_after\_stmt}}
 393 %  \CASE{\NT{stmt\_dots} \NT{nest\_after\_dots}}
 394 %  \CASE{\NT{decl\_stmt} \opt{\NT{nest\_after\_stmt}}}
 395 %
 396 %  \RULE{\rt{nest\_after\_exp}}
 397 %  \CASE{\NT{stmt\_dots} \NT{nest\_after\_dots}}
 398 %
 399 %  \RULE{\rt{toplevel\_after\_dots}}
 400 %  \CASE{\opt{\NT{toplevel\_after\_exp}}}
 401 %  \CASE{\NT{exp} \opt{\NT{toplevel\_after\_exp}}}
 402 %  \CASE{\NT{decl\_stmt\_expr} \NT{toplevel\_after\_stmt}}
 403 %
 404 %  \RULE{\rt{toplevel\_after\_exp}}
 405 %  \CASE{\NT{stmt\_dots} \opt{\NT{toplevel\_after\_dots}}}
 406 %
 407 %  \RULE{\rt{decl\_stmt\_expr}}
 408 %  \CASE{TMetaStmList$^\ddag$}
 409 %  \CASE{\NT{decl\_var}}
 410 %  \CASE{\NT{stmt}}
 411 %  \CASE{(\NT{stmt\_seq} \ANY{| \NT{stmt\_seq}})}
 412 %
 413 %  \RULE{\rt{toplevel\_after\_stmt}}
 414 %  \CASE{\NT{stmt\_dots} \opt{\NT{toplevel\_after\_dots}}}
 415 %  \CASE{\NT{decl\_stmt} \NT{toplevel\_after\_stmt}}
 416
 417 \end{grammar}
 418
 419 \begin{grammar}
 420   \RULE{\rt{OPTDOTSEQ}\mth{(}\rt{grammar\_ds}, \rt{when\_ds}\mth{)}}
 421   \CASE{}\multicolumn{3}{r}{\hspace{1cm}
 422   \KW{\opt{... \opt{\NT{when\_ds}}} \NT{grammar\_ds}
 423     \ANY{... \opt{\NT{when\_ds}} \NT{grammar\_ds}}
 424     \opt{... \opt{\NT{when\_ds}}}}
 425   }
 426
 427 %  \CASE{\opt{... \opt{\NT{when\_ds}}} \NT{grammar}
 428 %    \ANY{... \opt{\NT{when\_ds}} \NT{grammar}}
 429 %    \opt{... \opt{\NT{when\_ds}}}}
 430 %  \CASE{<... \any{\NT{when\_ds}} \NT{grammar} ...>}
 431 %  \CASE{<+... \any{\NT{when\_ds}} \NT{grammar} ...+>}
 432
 433 \end{grammar}
 434
 435 \noindent
 436 Lines may be annotated with an element of the set $\{\mtt{-}, \mtt{+},
 437 \mtt{*}\}$ or the singleton $\mtt{?}$, or one of each set. \mtt{?}
 438 represents at most one match of the given pattern. \mtt{*} is used for
 439 semantic match, \emph{i.e.}, a pattern that highlights the fragments
 440 annotated with \mtt{*}, but does not perform any modification of the
 441 matched code. \mtt{*} cannot be mixed with \mtt{-} and \mtt{+}.  There are
 442 some constraints on the use of these annotations:
 443 \begin{itemize}
 444 \item Dots, {\em i.e.} \texttt{...}, cannot occur on a line marked
 445   \texttt{+}.
 446 \item Nested dots, {\em i.e.}, dots enclosed in {\tt <} and {\tt >}, cannot
 447   occur on a line with any marking.
 448 \end{itemize}
 449
 450 Each element of a disjunction must be a proper term like an
 451 expression, a statement, an identifier or a declaration. Thus, the
 452 rule on the left below is not a syntaxically correct SmPL rule. One may
 453 use the rule on the right instead.
 454
 455 \begin{center}
 456   \begin{tabular}{l@{\hspace{5cm}}r}
 457 \begin{lstlisting}[language=Cocci]
 458 @@
 459 type T;
 460 T b;
 461 @@
 462
 463 (
 464  writeb(...,
 465 |
 466  readb(
 467 )
 468 @--(T)
 469  b)
 470 \end{lstlisting}
 471     &
 472 \begin{lstlisting}[language=Cocci]
 473 @@
 474 type T;
 475 T b;
 476 @@
 477
 478 (
 479 read
 480 |
 481 write
 482 )
 483  (...,
 484 @-- (T)
 485   b)
 486 \end{lstlisting}
 487     \\
 488   \end{tabular}
 489 \end{center}
 490
 491 \section{Types}
 492 \label{types}
 493
 494 \begin{grammar}
 495
 496   \RULE{\rt{ctypes}}
 497   \CASE{\NT{COMMA\_LIST}\mth{(}\NT{ctype}\mth{)}}
 498
 499   \RULE{\rt{ctype}}
 500   \CASE{\opt{\NT{const\_vol}} \NT{generic\_ctype} \any{*}}
 501   \CASE{\opt{\NT{const\_vol}} void \some{*}}
 502   \CASE{(\NT{ctype} \ANY{| \NT{ctype}})}
 503
 504   \RULE{\rt{const\_vol}}
 505   \CASE{const}
 506   \CASE{volatile}
 507
 508   \RULE{\rt{generic\_ctype}}
 509   \CASE{\NT{ctype\_qualif}}
 510   \CASE{\opt{\NT{ctype\_qualif}} char}
 511   \CASE{\opt{\NT{ctype\_qualif}} short}
 512   \CASE{\opt{\NT{ctype\_qualif}} int}
 513   \CASE{\opt{\NT{ctype\_qualif}} long}
 514   \CASE{\opt{\NT{ctype\_qualif}} long long}
 515   \CASE{double}
 516   \CASE{float}
 517   \CASE{\OPT{struct\OR union} \T{id} \OPT{\{ \any{\NT{struct\_decl\_list}} \}}}
 518
 519   \RULE{\rt{ctype\_qualif}}
 520   \CASE{unsigned}
 521   \CASE{signed}
 522
 523   \RULE{\rt{struct\_decl\_list}}
 524   \CASE{\NT{struct\_decl\_list\_start}}
 525
 526   \RULE{\rt{struct\_decl\_list\_start}}
 527   \CASE{\NT{struct\_decl}}
 528   \CASE{\NT{struct\_decl} \NT{struct\_decl\_list\_start}}
 529   \CASE{... \opt{when != \NT{struct\_decl}}$^\dag$ \opt{\NT{continue\_struct\_decl\_list}}}
 530
 531   \RULE{\rt{continue\_struct\_decl\_list}}
 532   \CASE{\NT{struct\_decl} \NT{struct\_decl\_list\_start}}
 533   \CASE{\NT{struct\_decl}}
 534
 535   \RULE{\rt{struct\_decl}}
 536   \CASE{\NT{ctype} \NT{d\_ident};}
 537   \CASE{\NT{fn\_ctype} (* \NT{d\_ident}) (\NT{PARAMSEQ}\mth{(}\NT{name\_opt\_decl}, \mth{\varepsilon)});)}
 538   \CASE{\opt{\NT{const\_vol}} \T{id} \NT{d\_ident};}
 539
 540   \RULE{\rt{d\_ident}}
 541   \CASE{\NT{id} \any{[\opt{\NT{expr}}]}}
 542
 543   \RULE{\rt{fn\_ctype}}
 544   \CASE{\NT{generic\_ctype} \any{*}}
 545   \CASE{void \any{*}}
 546
 547   \RULE{\rt{name\_opt\_decl}}
 548   \CASE{\NT{decl}}
 549   \CASE{\NT{ctype}}
 550   \CASE{\NT{fn\_ctype}}
 551 \end{grammar}
 552
 553 $^\dag$ The optional \texttt{when} construct ends at the end of the line.
 554
 555 \section{Function declarations}
 556
 557 \begin{grammar}
 558
 559   \RULE{\rt{fundecl}}
 560   \CASE{\opt{\NT{fn\_ctype}} \any{\NT{funinfo}} \NT{funid}
 561     (\opt{\NT{PARAMSEQ}\mth{(}\NT{param}, \mth{\varepsilon)}})
 562     \ttlb~\opt{\NT{stmt\_seq}} \ttrb}
 563
 564   \RULE{\rt{funproto}}
 565   \CASE{\opt{\NT{fn\_ctype}} \any{\NT{funinfo}} \NT{funid}
 566     (\opt{\NT{PARAMSEQ}\mth{(}\NT{param}, \mth{\varepsilon)}});}
 567
 568   \RULE{\rt{funinfo}}
 569   \CASE{inline}
 570   \CASE{\NT{storage}}
 571 %   \CASE{\NT{attr}}
 572
 573   \RULE{\rt{storage}}
 574   \CASE{static}
 575   \CASE{auto}
 576   \CASE{register}
 577   \CASE{extern}
 578
 579   \RULE{\rt{funid}}
 580   \CASE{\T{id}}
 581   \CASE{\mth{\T{metaid}^{\ssf{Id}}}}
 582 %   \CASE{\mth{\T{metaid}^{\ssf{Func}}}}
 583 %   \CASE{\mth{\T{metaid}^{\ssf{LocalFunc}}}}
 584
 585   \RULE{\rt{param}}
 586   \CASE{\NT{type} \T{id}}
 587   \CASE{\mth{\T{metaid}^{\ssf{Param}}}}
 588   \CASE{\mth{\T{metaid}^{\ssf{ParamList}}}}
 589
 590   \RULE{\rt{decl}}
 591   \CASE{\NT{ctype} \NT{id}}
 592   \CASE{\NT{fn\_ctype} (* \NT{id}) (\NT{PARAMSEQ}\mth{(}\NT{name\_opt\_decl}, \mth{\varepsilon)})}
 593   \CASE{void}
 594   \CASE{\mth{\T{metaid}^{\ssf{Param}}}}
 595 \end{grammar}
 596
 597 \begin{grammar}
 598   \RULE{\rt{PARAMSEQ}\mth{(}\rt{gram\_p}, \rt{when\_p}\mth{)}}
 599   \CASE{\NT{COMMA\_LIST}\mth{(}\NT{gram\_p} \OR \ldots \opt{\NT{when\_p}}\mth{)}}
 600 \end{grammar}
 601
 602 %\newpage
 603
 604 \section{Declarations}
 605
 606 \begin{grammar}
 607   \RULE{\rt{decl\_var}}
 608 %  \CASE{\NT{type} \opt{\NT{id} \opt{[\opt{\NT{dot\_expr}}]}
 609 %      \ANY{, \NT{id} \opt{[ \opt{\NT{dot\_expr}}]}}};}
 610   \CASE{\NT{common\_decl}}
 611   \CASE{\opt{\NT{storage}} \NT{ctype} \NT{COMMA\_LIST}\mth{(}\NT{d\_ident}\mth{)} ;}
 612   \CASE{\opt{\NT{storage}} \opt{\NT{const\_vol}} \T{id} \NT{COMMA\_LIST}\mth{(}\NT{d\_ident}\mth{)} ;}
 613   \CASE{\opt{\NT{storage}} \NT{fn\_ctype} ( * \NT{d\_ident} ) ( \NT{PARAMSEQ}\mth{(}\NT{name\_opt\_decl}, \mth{\varepsilon)} ) = \NT{initialize} ;}
 614   \CASE{typedef \NT{ctype} \NT{typedef\_ident} ;}
 615
 616   \RULE{\rt{one\_decl}}
 617   \CASE{\NT{common\_decl}}
 618   \CASE{\opt{\NT{storage}} \NT{ctype} \NT{id};}
 619 %  \CASE{\NT{storage} \NT{ctype} \NT{id} \opt{[\opt{\NT{dot\\_expr}}]} = \NT{nest\\_expr};}
 620   \CASE{\opt{\NT{storage}} \opt{\NT{const\_vol}} \T{id} \NT{d\_ident} ;}
 621
 622   \RULE{\rt{common\_decl}}
 623   \CASE{\NT{ctype};}
 624   \CASE{\NT{funproto}}
 625   \CASE{\opt{\NT{storage}} \NT{ctype} \NT{d\_ident} = \NT{initialize} ;}
 626   \CASE{\opt{\NT{storage}} \opt{\NT{const\_vol}} \T{id} \NT{d\_ident} = \NT{initialize} ;}
 627   \CASE{\opt{\NT{storage}} \NT{fn\_ctype} ( * \NT{d\_ident} ) ( \NT{PARAMSEQ}\mth{(}\NT{name\_opt\_decl}, \mth{\varepsilon)} ) ;}
 628   \CASE{\NT{decl\_ident} ( \OPT{\NT{COMMA\_LIST}\mth{(}\NT{expr}\mth{)}} ) ;}
 629
 630   \RULE{\rt{initialize}}
 631   \CASE{\NT{dot\_expr}}
 632   \CASE{\ttlb~\opt{\NT{COMMA\_LIST}\mth{(}\NT{dot\_expr}\mth{)}}~\ttrb}
 633
 634   \RULE{\rt{decl\_ident}}
 635   \CASE{\T{DeclarerId}}
 636   \CASE{\mth{\T{metaid}^{\ssf{Declarer}}}}
 637 \end{grammar}
 638
 639 \section{Statements}
 640
 641 The first rule {\em statement} describes the various forms of a statement.
 642 The remaining rules implement the constraints that are sensitive to the
 643 context in which the statement occurs: {\em single\_statement} for a
 644 context in which only one statement is allowed, and {\em decl\_statement}
 645 for a context in which a declaration, statement, or sequence thereof is
 646 allowed.
 647
 648 \begin{grammar}
 649   \RULE{\rt{stmt}}
 650   \CASE{\NT{include}}
 651   \CASE{\mth{\T{metaid}^{\ssf{Stmt}}}}
 652   \CASE{\NT{expr};}
 653   \CASE{if (\NT{dot\_expr}) \NT{single\_stmt} \opt{else \NT{single\_stmt}}}
 654   \CASE{for (\opt{\NT{dot\_expr}}; \opt{\NT{dot\_expr}}; \opt{\NT{dot\_expr}})
 655     \NT{single\_stmt}}
 656   \CASE{while (\NT{dot\_expr}) \NT{single\_stmt}}
 657   \CASE{do \NT{single\_stmt} while (\NT{dot\_expr});}
 658   \CASE{\NT{iter\_ident} (\any{\NT{dot\_expr}}) \NT{single\_stmt}}
 659   \CASE{switch (\opt{\NT{dot\_expr}}) \ttlb \any{\NT{case\_line}} \ttrb}
 660   \CASE{return \opt{\NT{dot\_expr}};}
 661   \CASE{\ttlb~\opt{\NT{stmt\_seq}} \ttrb}
 662   \CASE{\NT{NEST}\mth{(}\some{\NT{decl\_stmt}}, \NT{when}\mth{)}}
 663   \CASE{\NT{NEST}\mth{(}\NT{expr}, \NT{when}\mth{)}}
 664   \CASE{break;}
 665   \CASE{continue;}
 666   \CASE{\NT{id}:}
 667   \CASE{goto \NT{id};}
 668   \CASE{\ttlb \NT{stmt\_seq} \ttrb}
 669
 670   \RULE{\rt{single\_stmt}}
 671   \CASE{\NT{stmt}}
 672   \CASE{\NT{OR}\mth{(}\NT{stmt}\mth{)}}
 673
 674   \RULE{\rt{decl\_stmt}}
 675   \CASE{\mth{\T{metaid}^{\ssf{StmtList}}}}
 676   \CASE{\NT{decl\_var}}
 677   \CASE{\NT{stmt}}
 678   \CASE{\NT{OR}\mth{(}\NT{stmt\_seq}\mth{)}}
 679
 680   \RULE{\rt{stmt\_seq}}
 681   \CASE{\any{\NT{decl\_stmt}}
 682     \opt{\NT{DOTSEQ}\mth{(}\some{\NT{decl\_stmt}},
 683       \NT{when}\mth{)} \any{\NT{decl\_stmt}}}}
 684   \CASE{\any{\NT{decl\_stmt}}
 685     \opt{\NT{DOTSEQ}\mth{(}\NT{expr},
 686       \NT{when}\mth{)} \any{\NT{decl\_stmt}}}}
 687
 688   \RULE{\rt{case\_line}}
 689   \CASE{default :~\NT{stmt\_seq}}
 690   \CASE{case \NT{dot\_expr} :~\NT{stmt\_seq}}
 691
 692   \RULE{\rt{iter\_ident}}
 693   \CASE{\T{IteratorId}}
 694   \CASE{\mth{\T{metaid}^{\ssf{Iterator}}}}
 695 \end{grammar}
 696
 697 \begin{grammar}
 698   \RULE{\rt{OR}\mth{(}\rt{gram\_o}\mth{)}}
 699   \CASE{( \NT{gram\_o} \ANY{\ttmid \NT{gram\_o}})}
 700
 701   \RULE{\rt{DOTSEQ}\mth{(}\rt{gram\_d}, \rt{when\_d}\mth{)}}
 702   \CASE{\ldots \opt{\NT{when\_d}} \ANY{\NT{gram\_d} \ldots \opt{\NT{when\_d}}}}
 703
 704   \RULE{\rt{NEST}\mth{(}\rt{gram\_n}, \rt{when\_n}\mth{)}}
 705   \CASE{<\ldots \opt{\NT{when\_n}} \NT{gram\_n} \ANY{\ldots \opt{\NT{when\_n}} \NT{gram\_n}} \ldots>}
 706   \CASE{<+\ldots \opt{\NT{when\_n}} \NT{gram\_n} \ANY{\ldots \opt{\NT{when\_n}} \NT{gram\_n}} \ldots+>}
 707 \end{grammar}
 708
 709 \noindent
 710 OR is a macro that generates a disjunction of patterns.  The three
 711 tokens \T{(}, \T{\ttmid}, and \T{)} must appear in the leftmost
 712 column, to differentiate them from the parentheses and bit-or tokens
 713 that can appear within expressions (and cannot appear in the leftmost
 714 column). These token may also be preceded by \texttt{\bs}
 715 when they are used in an other column.  These tokens are furthermore
 716 different from (, \(\mid\), and ), which are part of the grammar
 717 metalanguage.
 718
 719 \section{Expressions}
 720
 721 A nest or a single ellipsis is allowed in some expression contexts, and
 722 causes ambiguity in others.  For example, in a sequence \mtt{\ldots
 723 \mita{expr} \ldots}, the nonterminal \mita{expr} must be instantiated as an
 724 explicit C-language expression, while in an array reference,
 725 \mtt{\mth{\mita{expr}_1} \mtt{[} \mth{\mita{expr}_2} \mtt{]}}, the
 726 nonterminal \mth{\mita{expr}_2}, because it is delimited by brackets, can
 727 be also instantiated as \mtt{\ldots}, representing an arbitrary expression.  To
 728 distinguish between the various possibilities, we define three nonterminals
 729 for expressions: {\em expr} does not allow either top-level nests or
 730 ellipses, {\em nest\_expr} allows a nest but not an ellipsis, and {\em
 731 dot\_expr} allows both.  The EXPR macro is used to express these variants
 732 in a concise way.
 733
 734 \begin{grammar}
 735   \RULE{\rt{expr}}
 736   \CASE{\NT{EXPR}\mth{(}\NT{expr}\mth{)}}
 737
 738   \RULE{\rt{nest\_expr}}
 739   \CASE{\NT{EXPR}\mth{(}\NT{nest\_expr}\mth{)}}
 740   \CASE{\NT{NEST}\mth{(}\NT{nest\_expr}, \NT{exp\_whencode}\mth{)}}
 741
 742   \RULE{\rt{dot\_expr}}
 743   \CASE{\NT{EXPR}\mth{(}\NT{dot\_expr}\mth{)}}
 744   \CASE{\NT{NEST}\mth{(}\NT{dot\_expr}, \NT{exp\_whencode}\mth{)}}
 745   \CASE{...~\opt{\NT{exp\_whencode}}}
 746
 747   \RULE{\rt{EXPR}\mth{(}\rt{exp}\mth{)}}
 748   \CASE{\NT{exp} \NT{assign\_op} \NT{exp}}
 749   \CASE{\NT{exp}++}
 750   \CASE{\NT{exp}--}
 751   \CASE{\NT{unary\_op} \NT{exp}}
 752   \CASE{\NT{exp} \NT{bin\_op} \NT{exp}}
 753   \CASE{\NT{exp} ?~\NT{dot\_expr} :~\NT{exp}}
 754   \CASE{(\NT{type}) \NT{exp}}
 755   \CASE{\NT{exp} [\NT{dot\_expr}]}
 756   \CASE{\NT{exp} .~\NT{id}}
 757   \CASE{\NT{exp} -> \NT{id}}
 758   \CASE{\NT{exp}(\opt{\NT{PARAMSEQ}\mth{(}\NT{arg}, \NT{exp\_whencode}\mth{)}})}
 759   \CASE{\NT{id}}
 760 %   \CASE{\mth{\T{metaid}^{\ssf{Func}}}}
 761 %   \CASE{\mth{\T{metaid}^{\ssf{LocalFunc}}}}
 762   \CASE{\mth{\T{metaid}^{\ssf{Exp}}}}
 763 %   \CASE{\mth{\T{metaid}^{\ssf{Err}}}}
 764   \CASE{\mth{\T{metaid}^{\ssf{Const}}}}
 765   \CASE{\NT{const}}
 766   \CASE{(\NT{dot\_expr})}
 767   \CASE{\NT{OR}\mth{(}\NT{exp}\mth{)}}
 768
 769   \RULE{\rt{arg}}
 770   \CASE{\NT{nest\_expr}}
 771   \CASE{\mth{\T{metaid}^{\ssf{ExpList}}}}
 772
 773   \RULE{\rt{exp\_whencode}}
 774   \CASE{when != \NT{expr}}
 775
 776   \RULE{\rt{assign\_op}}
 777   \CASE{= \OR -= \OR += \OR *= \OR /= \OR \%=}
 778   \CASE{\&= \OR |= \OR \caret= \OR \lt\lt= \OR \gt\gt=}
 779
 780   \RULE{\rt{bin\_op}}
 781   \CASE{* \OR / \OR \% \OR + \OR -}
 782   \CASE{\lt\lt \OR \gt\gt \OR \caret\xspace \OR \& \OR \ttmid}
 783   \CASE{< \OR > \OR <= \OR >= \OR == \OR != \OR \&\& \OR \ttmid\ttmid}
 784
 785   \RULE{\rt{unary\_op}}
 786   \CASE{++ \OR -- \OR \& \OR * \OR + \OR - \OR !}
 787
 788 \end{grammar}
 789
 790 \section{Constant, Identifiers and Types for Transformations}
 791
 792 \begin{grammar}
 793   \RULE{\rt{const}}
 794   \CASE{\NT{string}}
 795   \CASE{[0-9]+}
 796   \CASE{\mth{\cdots}}
 797
 798   \RULE{\rt{string}}
 799   \CASE{"\any{[\^{}"]}"}
 800
 801   \RULE{\rt{id}}
 802   \CASE{\T{id} \OR \mth{\T{metaid}^{\ssf{Id}}}}
 803
 804   \RULE{\rt{typedef\_ident}}
 805   \CASE{\T{id} \OR \mth{\T{metaid}^{\ssf{Type}}}}
 806
 807   \RULE{\rt{type}}
 808   \CASE{\NT{ctype} \OR \mth{\T{metaid}^{\ssf{Type}}}}
 809
 810   \RULE{\rt{pathToIsoFile}}
 811   \CASE{<.*>}
 812
 813   \RULE{\rt{regexp}}
 814   \CASE{"\any{[\^{}"]}"}
 815 \end{grammar}
 816
 817
 818 %%% Local Variables:
 819 %%% mode: LaTeX
 820 %%% TeX-master: "main_grammar"
 821 %%% coding: utf-8
 822 %%% TeX-PDF-mode: t
 823 %%% ispell-local-dictionary: "american"
 824 %%% End: