regcomp.c

硬盘各项性能的测试,如温度容量版本健康度型号

  return (int) ret;
}
#ifdef _LIBC
weak_alias (__regcomp, regcomp)
#endif

/* Returns a message corresponding to an error code, ERRCODE, returned
   from either regcomp or regexec.   We don't use PREG here.  */

size_t
regerror (errcode, preg, errbuf, errbuf_size)
    int errcode;
    const regex_t *preg;
    char *errbuf;
    size_t errbuf_size;
{
  const char *msg;
  size_t msg_size;

  if (BE (errcode < 0
	  || errcode >= (int) (sizeof (__re_error_msgid_idx)
			       / sizeof (__re_error_msgid_idx[0])), 0))
    /* Only error codes returned by the rest of the code should be passed
       to this routine.  If we are given anything else, or if other regex
       code generates an invalid error code, then the program has a bug.
       Dump core so we can fix it.  */
    abort ();

  msg = gettext (__re_error_msgid + __re_error_msgid_idx[errcode]);

  msg_size = strlen (msg) + 1; /* Includes the null.  */

  if (BE (errbuf_size != 0, 1))
    {
      if (BE (msg_size > errbuf_size, 0))
	{
#if defined HAVE_MEMPCPY || defined _LIBC
	  *((char *) __mempcpy (errbuf, msg, errbuf_size - 1)) = '\0';
#else
	  memcpy (errbuf, msg, errbuf_size - 1);
	  errbuf[errbuf_size - 1] = 0;
#endif
	}
      else
	memcpy (errbuf, msg, msg_size);
    }

  return msg_size;
}
#ifdef _LIBC
weak_alias (__regerror, regerror)
#endif


static void
free_dfa_content (re_dfa_t *dfa)
{
  int i, j;

  re_free (dfa->subexps);

  for (i = 0; i < dfa->nodes_len; ++i)
    {
      re_token_t *node = dfa->nodes + i;
#ifdef RE_ENABLE_I18N
      if (node->type == COMPLEX_BRACKET && node->duplicated == 0)
	free_charset (node->opr.mbcset);
      else
#endif /* RE_ENABLE_I18N */
	if (node->type == SIMPLE_BRACKET && node->duplicated == 0)
	  re_free (node->opr.sbcset);
    }
  re_free (dfa->nexts);
  for (i = 0; i < dfa->nodes_len; ++i)
    {
      if (dfa->eclosures != NULL)
	re_node_set_free (dfa->eclosures + i);
      if (dfa->inveclosures != NULL)
	re_node_set_free (dfa->inveclosures + i);
      if (dfa->edests != NULL)
	re_node_set_free (dfa->edests + i);
    }
  re_free (dfa->edests);
  re_free (dfa->eclosures);
  re_free (dfa->inveclosures);
  re_free (dfa->nodes);

  for (i = 0; i <= dfa->state_hash_mask; ++i)
    {
      struct re_state_table_entry *entry = dfa->state_table + i;
      for (j = 0; j < entry->num; ++j)
	{
	  re_dfastate_t *state = entry->array[j];
	  free_state (state);
	}
      re_free (entry->array);
    }
  re_free (dfa->state_table);

  if (dfa->word_char != NULL)
    re_free (dfa->word_char);
#ifdef DEBUG
  re_free (dfa->re_str);
#endif

  re_free (dfa);
}


/* Free dynamically allocated space used by PREG.  */

void
regfree (preg)
    regex_t *preg;
{
  re_dfa_t *dfa = (re_dfa_t *) preg->buffer;
  if (BE (dfa != NULL, 1))
    free_dfa_content (dfa);

  re_free (preg->fastmap);
}
#ifdef _LIBC
weak_alias (__regfree, regfree)
#endif

/* Entry points compatible with 4.2 BSD regex library.  We don't define
   them unless specifically requested.  */

#if defined _REGEX_RE_COMP || defined _LIBC

/* BSD has one and only one pattern buffer.  */
static struct re_pattern_buffer re_comp_buf;

char *
# ifdef _LIBC
/* Make these definitions weak in libc, so POSIX programs can redefine
   these names if they don't use our functions, and still use
   regcomp/regexec above without link errors.  */
weak_function
# endif
re_comp (s)
     const char *s;
{
  reg_errcode_t ret;
  char *fastmap;

  if (!s)
    {
      if (!re_comp_buf.buffer)
	return gettext ("No previous regular expression");
      return 0;
    }

  if (re_comp_buf.buffer)
    {
      fastmap = re_comp_buf.fastmap;
      re_comp_buf.fastmap = NULL;
      __regfree (&re_comp_buf);
      memset (&re_comp_buf, '\0', sizeof (re_comp_buf));
      re_comp_buf.fastmap = fastmap;
    }

  if (re_comp_buf.fastmap == NULL)
    {
      re_comp_buf.fastmap = (char *) malloc (SBC_MAX);
      if (re_comp_buf.fastmap == NULL)
	return (char *) gettext (__re_error_msgid
				 + __re_error_msgid_idx[(int) REG_ESPACE]);
    }

  /* Since `re_exec' always passes NULL for the `regs' argument, we
     don't need to initialize the pattern buffer fields which affect it.  */

  /* Match anchors at newlines.  */
  re_comp_buf.newline_anchor = 1;

  ret = re_compile_internal (&re_comp_buf, s, strlen (s), re_syntax_options);

  if (!ret)
    return NULL;

  /* Yes, we're discarding `const' here if !HAVE_LIBINTL.  */
  return (char *) gettext (__re_error_msgid + __re_error_msgid_idx[(int) ret]);
}

#ifdef _LIBC
libc_freeres_fn (free_mem)
{
  __regfree (&re_comp_buf);
}
#endif

#endif /* _REGEX_RE_COMP */

/* Internal entry point.
   Compile the regular expression PATTERN, whose length is LENGTH.
   SYNTAX indicate regular expression's syntax.  */

static reg_errcode_t
re_compile_internal (preg, pattern, length, syntax)
     regex_t *preg;
     const char * pattern;
     int length;
     reg_syntax_t syntax;
{
  reg_errcode_t err = REG_NOERROR;
  re_dfa_t *dfa;
  re_string_t regexp;

  /* Initialize the pattern buffer.  */
  preg->fastmap_accurate = 0;
  preg->syntax = syntax;
  preg->not_bol = preg->not_eol = 0;
  preg->used = 0;
  preg->re_nsub = 0;
  preg->can_be_null = 0;
  preg->regs_allocated = REGS_UNALLOCATED;

  /* Initialize the dfa.  */
  dfa = (re_dfa_t *) preg->buffer;
  if (preg->allocated < sizeof (re_dfa_t))
    {
      /* If zero allocated, but buffer is non-null, try to realloc
	 enough space.  This loses if buffer's address is bogus, but
	 that is the user's responsibility.  If ->buffer is NULL this
	 is a simple allocation.  */
      dfa = re_realloc (preg->buffer, re_dfa_t, 1);
      if (dfa == NULL)
	return REG_ESPACE;
      preg->allocated = sizeof (re_dfa_t);
    }
  preg->buffer = (unsigned char *) dfa;
  preg->used = sizeof (re_dfa_t);

  err = init_dfa (dfa, length);
  if (BE (err != REG_NOERROR, 0))
    {
      re_free (dfa);
      preg->buffer = NULL;
      preg->allocated = 0;
      return err;
    }
#ifdef DEBUG
  dfa->re_str = re_malloc (char, length + 1);
  strncpy (dfa->re_str, pattern, length + 1);
#endif

  err = re_string_construct (&regexp, pattern, length, preg->translate,
			     syntax & RE_ICASE);
  if (BE (err != REG_NOERROR, 0))
    {
      re_free (dfa);
      preg->buffer = NULL;
      preg->allocated = 0;
      return err;
    }

  /* Parse the regular expression, and build a structure tree.  */
  preg->re_nsub = 0;
  dfa->str_tree = parse (&regexp, preg, syntax, &err);
  if (BE (dfa->str_tree == NULL, 0))
    goto re_compile_internal_free_return;

  /* Analyze the tree and collect information which is necessary to
     create the dfa.  */
  err = analyze (dfa);
  if (BE (err != REG_NOERROR, 0))
    goto re_compile_internal_free_return;

  /* Then create the initial state of the dfa.  */
  err = create_initial_state (dfa);

  /* Release work areas.  */
  free_workarea_compile (preg);
  re_string_destruct (&regexp);

  if (BE (err != REG_NOERROR, 0))
    {
    re_compile_internal_free_return:
      free_dfa_content (dfa);
      preg->buffer = NULL;
      preg->allocated = 0;
    }

  return err;
}

/* Initialize DFA.  We use the length of the regular expression PAT_LEN
   as the initial length of some arrays.  */

static reg_errcode_t
init_dfa (dfa, pat_len)
     re_dfa_t *dfa;
     int pat_len;
{
  int table_size;

  memset (dfa, '\0', sizeof (re_dfa_t));

  dfa->nodes_alloc = pat_len + 1;
  dfa->nodes = re_malloc (re_token_t, dfa->nodes_alloc);

  dfa->states_alloc = pat_len + 1;

  /*  table_size = 2 ^ ceil(log pat_len) */
  for (table_size = 1; table_size > 0; table_size <<= 1)
    if (table_size > pat_len)
      break;

  dfa->state_table = calloc (sizeof (struct re_state_table_entry), table_size);
  dfa->state_hash_mask = table_size - 1;

  dfa->subexps_alloc = 1;
  dfa->subexps = re_malloc (re_subexp_t, dfa->subexps_alloc);
  dfa->word_char = NULL;

  if (BE (dfa->nodes == NULL || dfa->state_table == NULL
	  || dfa->subexps == NULL, 0))
    {
      /* We don't bother to free anything which was allocated.  Very
	 soon the process will go down anyway.  */
      dfa->subexps = NULL;
      dfa->state_table = NULL;
      dfa->nodes = NULL;
      return REG_ESPACE;
    }
  return REG_NOERROR;
}

/* Initialize WORD_CHAR table, which indicate which character is
   "word".  In this case "word" means that it is the word construction
   character used by some operators like "\<", "\>", etc.  */

static reg_errcode_t
init_word_char (dfa)
     re_dfa_t *dfa;
{
  int i, j, ch;
  dfa->word_char = (re_bitset_ptr_t) calloc (sizeof (bitset), 1);
  if (BE (dfa->word_char == NULL, 0))
    return REG_ESPACE;
  for (i = 0, ch = 0; i < BITSET_UINTS; ++i)
    for (j = 0; j < UINT_BITS; ++j, ++ch)
      if (isalnum (ch) || ch == '_')
	dfa->word_char[i] |= 1 << j;
  return REG_NOERROR;
}

/* Free the work area which are only used while compiling.  */

static void
free_workarea_compile (preg)
     regex_t *preg;
{
  re_dfa_t *dfa = (re_dfa_t *) preg->buffer;
  free_bin_tree (dfa->str_tree);
  dfa->str_tree = NULL;
  re_free (dfa->org_indices);
  dfa->org_indices = NULL;
}

/* Create initial states for all contexts.  */

static reg_errcode_t
create_initial_state (dfa)
     re_dfa_t *dfa;
{
  int first, i;
  reg_errcode_t err;
  re_node_set init_nodes;

  /* Initial states have the epsilon closure of the node which is
     the first node of the regular expression.  */
  first = dfa->str_tree->first;
  dfa->init_node = first;
  err = re_node_set_init_copy (&init_nodes, dfa->eclosures + first);
  if (BE (err != REG_NOERROR, 0))
    return err;

  /* The back-references which are in initial states can epsilon transit,
     since in this case all of the subexpressions can be null.
     Then we add epsilon closures of the nodes which are the next nodes of
     the back-references.  */
  if (dfa->nbackref > 0)
    for (i = 0; i < init_nodes.nelem; ++i)
      {
	int node_idx = init_nodes.elems[i];
	re_token_type_t type = dfa->nodes[node_idx].type;

	int clexp_idx;
	if (type != OP_BACK_REF)
	  continue;
	for (clexp_idx = 0; clexp_idx < init_nodes.nelem; ++clexp_idx)
	  {
	    re_token_t *clexp_node;
	    clexp_node = dfa->nodes + init_nodes.elems[clexp_idx];
	    if (clexp_node->type == OP_CLOSE_SUBEXP
		&& clexp_node->opr.idx + 1 == dfa->nodes[node_idx].opr.idx)
	      break;
	  }
	if (clexp_idx == init_nodes.nelem)
	  continue;

	if (type == OP_BACK_REF)
	  {
	    int dest_idx = dfa->edests[node_idx].elems[0];
	    if (!re_node_set_contains (&init_nodes, dest_idx))
	      {
		re_node_set_merge (&init_nodes, dfa->eclosures + dest_idx);
		i = 0;
	      }
	  }
      }

  /* It must be the first time to invoke acquire_state.  */
  dfa->init_state = re_acquire_state_context (&err, dfa, &init_nodes, 0);
  /* We don't check ERR here, since the initial state must not be NULL.  */
  if (BE (dfa->init_state == NULL, 0))
    return err;
  if (dfa->init_state->has_constraint)
    {
      dfa->init_state_word = re_acquire_state_context (&err, dfa, &init_nodes,
						       CONTEXT_WORD);
      dfa->init_state_nl = re_acquire_state_context (&err, dfa, &init_nodes,
						     CONTEXT_NEWLINE);
      dfa->init_state_begbuf = re_acquire_state_context (&err, dfa,
							 &init_nodes,
							 CONTEXT_NEWLINE
							 | CONTEXT_BEGBUF);
      if (BE (dfa->init_state_word == NULL || dfa->init_state_nl == NULL
	      || dfa->init_state_begbuf == NULL, 0))
	return err;
    }
  else
    dfa->init_state_word = dfa->init_state_nl
      = dfa->init_state_begbuf = dfa->init_state;

  re_node_set_free (&init_nodes);
  return REG_NOERROR;
}

/* Analyze the structure tree, and calculate "first", "next", "edest",
   "eclosure", and "inveclosure".  */

static reg_errcode_t
analyze (dfa)
     re_dfa_t *dfa;
{
  int i;
  reg_errcode_t ret;

  /* Allocate arrays.  */
  dfa->nexts = re_malloc (int, dfa->nodes_alloc);
  dfa->org_indices = re_malloc (int, dfa->nodes_alloc);
  dfa->edests = re_malloc (re_node_set, dfa->nodes_alloc);
  dfa->eclosures = re_malloc (re_node_set, dfa->nodes_alloc);
  dfa->inveclosures = re_malloc (re_node_set, dfa->nodes_alloc);
  if (BE (dfa->nexts == NULL || dfa->org_indices == NULL || dfa->edests == NULL
	  || dfa->eclosures == NULL || dfa->inveclosures == NULL, 0))
    return REG_ESPACE;
  /* Initialize them.  */
  for (i = 0; i < dfa->nodes_len; ++i)
    {
      dfa->nexts[i] = -1;
      re_node_set_init_empty (dfa->edests + i);