Code Search for Developers
 
 
  

misc_parse.c from EmStar at Krugle


Show misc_parse.c syntax highlighted

/*
 *
 * Copyright (c) 2003 The Regents of the University of California.  All 
 * rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * - Redistributions of source code must retain the above copyright
 *   notice, this list of conditions and the following disclaimer.
 *
 * - Neither the name of the University nor the names of its
 *   contributors may be used to endorse or promote products derived
 *   from this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS''
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
 * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
 * PARTICULAR  PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR
 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 */
 


/*
 *  misc_parse.c
 * 
 *  Some simple parsing functions
 *
 */

#include <libmisc/misc.h>
#include <glib.h>

int misc_num_args(char *str, char esc)
{
  char *ptr;
  int arg = 0, retval = 0;
  
  /* if null argument or null string passed, then we return 0 */
  if ((str == NULL) || (*str == '\0'))
    goto done;
  
  for (ptr = str; *ptr; ptr++) {
    
    /* every non-esc char is an arg */
    if (*ptr != esc) {
      arg = 1;
      continue;
    }

    /* find first esc char after an arg */
    if (arg && (*ptr == esc)) {
      arg = 0;
      /* we count args once we find the first esc after the arg */
      retval++;  
      continue;
    }
    
    /* multiple consecutive esc after an arg are ignored, 
     * i.e.: arg == 0 && ptr == esc */
  }
  
  /* if string ended with an arg and no esc, then we add the last arg
   * in the total count */
  if (arg)
    retval++;

done:
  return retval;
}


char * misc_parse_string(char *str, char esc, char **val)
{
  char *ptr;
  int arg = 0;
  int esc_mode = 0;
  
  /* if null argument or null string passed, then we return NULL */
  if ((str == NULL) || (*str == '\0'))
    return NULL;
  
  for (ptr = str; *ptr; ptr++) {
    
    /* esc chars at the beginning of the string are ignored */
    
    /* every non-esc char is an arg */
    if ((*ptr != esc) && !esc_mode) {
      /* get rid of the first esc chars, if any */
      if (!arg) str = ptr;
      arg = 1;
      continue;
    }

    /* find first esc char after an arg */
    if (arg && (*ptr == esc)) {
      arg = 0;
      /* terminate string */
      *ptr = '\0';
      esc_mode = 1;    
      continue;
    }
    
    /* get rid of multiple consecutive esc char after the arg */
    if (esc_mode && (*ptr != esc))
      break;
  }

  /* copy first argument if necessary */
  if (val != NULL) {
    if (esc_mode || arg)
      *val = strdup(str);
    else
      *val = NULL;  
  }

  return ptr;
}


void misc_parse_unescape(char *str, char esc)
{
  char *ptr;
  char *trail;
  int esc_mode = 0;

  if (str == NULL) return;

  for (trail=str, ptr=str; *ptr; ptr++) {
    if (!esc_mode && (*ptr == esc)) {
      esc_mode = 1;
      continue;
    }

    esc_mode = 0;
    *trail = *ptr;
    trail++;
  }
  
  /* null term */
  *trail = 0;
}


void misc_parse_reset(parser_state_t *state)
{
  if (state && state->_input) {
    free(state->_input);
    state->_input = NULL;
  }  
  state->consumed = 0;
}


parser_state_t * misc_parse_init(char *input, int scheme)
{
  parser_state_t *ps = g_new0(parser_state_t, 1);
  ps->input = input;

  switch (scheme) {
  default:
  case MISC_PARSE_COLON_SCHEME:
    break;

  case MISC_PARSE_SEMICOLON_SCHEME:
    ps->pair_delimit_set = ";";
    break;

  case MISC_PARSE_SEMICOLON_KEY_SCHEME:
    ps->pair_delimit_set = ";";
    ps->pair_assign_set = "";
    break;

  case MISC_PARSE_COMMA_SCHEME:
    ps->pair_delimit_set = ",";
    break;

  case MISC_PARSE_LF_SCHEME:
    ps->pair_delimit_set = "\n";
    ps->pair_assign_set = "";
    break;

  // dootcam returns strings with ampersands as delimiters
  case MISC_PARSE_AMPERSAND_SCHEME:
    ps->pair_delimit_set = "&";
    break;

  }
  return ps;
}

void misc_parse_cleanup(parser_state_t *state)
{
  misc_parse_reset(state);
  free(state);
}


int misc_parse_n_args(parser_state_t *state, char **keys, char **vals, int n)
{
  int i;
  
  memset(vals, 0, sizeof(char*)*n);

  for (i=0; i<n; i++) {
    if (misc_parse_next_kvp(state) < 0)
      return -1;

    if (state->value) {
      if (keys && strcmp(state->key, keys[i])) {
	elog(LOG_WARNING, "Argument key mismatch: %s,%s", 
	     keys[i], state->key);
	return -1;
      }
      vals[i] = strdup(state->value);
    }
    else 
      vals[i] = strdup(state->key);
  }

  /* check for nothing left.. */
  if (misc_parse_next_kvp(state) < 0)
    return 0;

  /* some kind of string remains.. */
  if (state->key && state->key[0])
    return -1;

  /* ok */
  return 0;
}


void misc_free_n_args(char **args, int n)
{
  int i;
  for (i=0; i<n; i++)
    if (args[i]) free(args[i]);
}


char *misc_parse_get_raw_value(parser_state_t *state, int *remain)
{
  int offset;

  if (state->value == NULL)
    return NULL;

  offset = state->value - state->_input;
  if (remain) *remain = state->input_len - offset;
  return state->input + offset;
}


int misc_parse_next_kvp(parser_state_t *state)
{
  char *pair_dset = NULL;
  char *pair_aset = NULL;
  int esc_mode = 0;
  int found_pair = 0;

  /* 
   * initialization with defaults 
   */

  /* default length */
  if (state->input_len == 0) 
    state->input_len = strlen(state->input);

  /* copy input if needed, force null term */
  if (state->_input == NULL) {
    state->_input = malloc(state->input_len+1);
    memmove(state->_input, state->input, state->input_len);
    state->_input[state->input_len] = 0;
    //state->_input[state->input_len+1] = 0;
  }
  
  /* default delimiter set */
  if (state->pair_delimit_set)
    pair_dset = state->pair_delimit_set;
  else
    pair_dset = ":\n";

  /* default assignment set */
  if (state->pair_assign_set)
    pair_aset = state->pair_assign_set;
  else
    pair_aset = "=";

  /* default escape */
  if (state->escape_char == 0)
    state->escape_char = '\\';

  /* 
   * parse buffer
   */

  /* init */
  state->key = state->_input + state->consumed;
  state->value = NULL;
  state->pair_delimit = 0;
  state->pair_assign = 0;

  /* if we're starting out with no data, we're done */
  if (state->consumed == state->input_len) 
    goto check_reset;

  /* otherwise scan for next key */
  while (state->consumed <= state->input_len) {
    
    char c = state->_input[state->consumed];
    
    /* if last char, force out of esacpe mode */
    if (state->consumed == state->input_len)
      esc_mode = 0;
    
    /* check for escape char */
    if (c == state->escape_char) {
      esc_mode = 1;
      goto nextchar;
    }
    
    /* escape mode? */
    if (esc_mode) {
      esc_mode = 0;
      goto nextchar;
    }
    
    /* check for pair delimiter */
    if ((c == 0) || strchr(pair_dset, c))
      goto got_pair;
    
    /* check for assign delimiter, unless second one.. */
    if ((state->value == NULL) && strchr(pair_aset, c)) 
      goto got_assign;
    
    /* ok, next char */
    goto nextchar;
    
  got_pair:
    /* record delimiter */
    state->pair_delimit = c;
    
    /* we found a pair */
    found_pair = 1;
    
    /* null term, advance, done */
    state->_input[state->consumed] = 0;
    state->consumed++;
    goto unescape;
    
  got_assign:
    /* record delimit and null */
    state->pair_assign = c;
    state->_input[state->consumed] = 0;
    state->value = state->_input + state->consumed+1;
    /* fall through */
    
  nextchar:
    state->consumed++;
  }
  
 check_reset:
  /* no new pair.. reset */
  if (found_pair == 0) {
    misc_parse_reset(state);
    return -1;
  }

 unescape:
  misc_parse_unescape(state->key, state->escape_char);
  misc_parse_unescape(state->value, state->escape_char);

  return state->pair_delimit;
}


void misc_parse_dump_curr_to_buf(buf_t *buf, parser_state_t *state)
{
  bufprintf(buf, "%s", state->key);
  if ((state->pair_assign) && (state->value)) {
    bufprintf(buf, "%c%s", state->pair_assign, state->value);
  }
  bufprintf(buf, "%c", state->pair_delimit);
}


char **misc_parse_csv_to_vector(char *str)
{
  buf_t buf;
  parser_state_t *ps = misc_parse_init(str, MISC_PARSE_COMMA_SCHEME);
  
  buf_init(&buf);
  while (misc_parse_next_kvp(ps) >= 0) {
    char *dup = strdup(ps->key);
    bufcpy(&buf, &dup, sizeof(dup));
  }
  {
    int x=0;
    bufcpy(&buf, &x, sizeof(x));
  }

  misc_parse_cleanup(ps);

  return (char**)buf.buf;
}


void misc_usage_uniquify(buf_t *in, buf_t *out)
{
  parser_state_t *ps = misc_parse_init(in->buf, MISC_PARSE_LF_SCHEME);
  buf_t *strs = buf_new();
  buf_iter_t *iter = buf_item_iter_new(strs);
  int header = 1;

  while (misc_parse_next_kvp(ps) >= 0) {
    char *ptr;

    /* keep only the first entry with no preceding whitespace */
    if (!isspace(ps->key[0])) {
      if (header) {
	header = 0;
	goto keep;
      }
      goto skip;
    }

    /* extract the key */
    ptr = strpbrk(ps->key, ":=");
    if (ptr) { 
      char save = *ptr;
      *ptr = 0;
      for (buf_item_iter_top(iter); buf_item_iter_valid(iter); 
	   buf_item_iter_next(iter)) {
	if (strncmp(buf_item_iter_get_pointer(iter, -1), ps->key, 
		    buf_item_iter_length(iter)) == 0) 
	  goto skip;
      }
      buf_item_iter_append_str(iter, ps->key, strlen(ps->key));
      *ptr = save;
    }

  keep:
    bufprintf(out, "%s\n", ps->key);

  skip:
    continue;
  }

  buf_item_iter_destroy(iter, 1);
  misc_parse_cleanup(ps);
}



int misc_parse_test_key(parser_state_t *state, char *key)
{
  return strcasecmp(state->key, key) == 0;
}




See more files for this project here

EmStar

EmStar is a software system for developing and deploying wireless sensor networks involving Linux-based platforms. As the wireless sensor network community has attempted to deploy more complex designs---large-scale, long-lived systems that need self-organization and adaptivity---a number of difficult software design issues have arisen. Advances in software design have not kept pace with the capabilities of hardware. This is because designing for an adaptive, efficient, and useful sensor network has turned out to be surprisingly complex and difficult. EmStar is a Linux-based software framework, whose goal is to dramatically reduce this complexity, enabling work to be shared and reused, and simplifying and speeding the design of new sensor network applications.

Project homepage: http://cvs.cens.ucla.edu/emstar/
Programming language(s): C,Shell Script
License: other

  elog.c
  elog_emit.c
  file.c
  misc_angles.c
  misc_buf.c
  misc_crc32.c
  misc_filename.c
  misc_hash.c
  misc_init.c
  misc_lock.c
  misc_math.c
  misc_namelist.c
  misc_network.c
  misc_nmea.c
  misc_opt.c
  misc_parse.c
  misc_proc.c
  misc_random.c
  misc_ringbuff.c
  misc_serial.c
  misc_signals.c
  misc_sim.c
  misc_time.c
  misc_types.c
  misc_version.c
  string.c