This patch improves the parser used by Cactus to prepocess parameter

files.

The main changes are:

- when reading a parameter file do not parse the file while reading,
  but read it first into a buffer, preprocess that and parse the
  buffer after that
- replace the code which changes $parfile into the parameter file
  name to use this buffer preprocessing
- replace $ENV{'*'} "defines" by environment variable values (*),
  e.g. $ENV{'HOME'} with $HOME.

Frank


git-svn-id: http://svn.cactuscode.org/flesh/trunk@4573 17b73243-c579-4c4c-a9d2-2d5706c11dac

1 files changed, 455 insertions, 192 deletions

diff --git a/src/util/ParseFile.c b/src/util/ParseFile.c
index 86172217..bd6bd71e 100644
--- a/src/util/ParseFile.c
+++ b/src/util/ParseFile.c
@@ -7,7 +7,6 @@
               to a user-supplied subroutine.
               Currently taken from the old cactus ones and slightly modifed.
    @enddesc
-   @version   $Id$
  @@*/
 
 /*#define DEBUG*/
@@ -15,6 +14,9 @@
 #include <stdio.h>
 #include <string.h>
 #include <stdlib.h>
+#include <string.h>
+
+#include <cctk.h>
 
 #include "cctk_Flesh.h"
 #include "cctk_CommandLine.h"
@@ -38,6 +40,11 @@ CCTK_FILEVERSION(util_ParseFile_c);
 
 static void CheckBuf(int, int);
 static void removeSpaces(char *stripMe);
+static char *ReadFile(FILE *file, unsigned long *filesize);
+static char *ParseDefines(char *buffer, unsigned long *buffersize);
+int ParseBuffer(char *buffer,
+                int (*set_function)(const char *, const char *, int),
+                tFleshConfig *ConfigData);
 
 /********************************************************************
  ********************* Other Routine Prototypes *********************
@@ -63,7 +70,7 @@ static int lineno = 1;
 
  /*@@
    @routine ParseFile
-   @author Paul Walker
+   @author Paul Walker, Frank Loeffler
    @desc
    This routine actually parses the parameter file. The
    syntax we allow is
@@ -83,6 +90,7 @@ static int lineno = 1;
    @hdesc Moved to CCTK.
           Changed to pass data to arbitrary function.
           Changed to take a file descriptor rather than a filename.
+          Use a buffer to parse which can be preprocessed before main parsing
    @endhistory
    @var     ifp
    @vdesc   The filestream to parse
@@ -111,10 +119,434 @@ static int lineno = 1;
    0 - success
    @endreturndesc
 @@*/
+
 int ParseFile(FILE *ifp,
               int (*set_function)(const char *, const char *, int),
               tFleshConfig *ConfigData)
 {
+  int retval;
+  unsigned long buffersize;
+  char *buffer = ReadFile(ifp, &buffersize);
+  if (!buffer)
+    return 1;
+  buffer = ParseDefines(buffer, &buffersize);
+  retval = ParseBuffer(buffer, set_function, ConfigData);
+  free(buffer);
+  return retval;
+}
+
+/********************************************************************
+ *********************     Local Routines   *************************
+ ********************************************************************/
+
+ /*@@
+   @routine CheckBuf
+   @author Paul Walker
+   @desc
+   A simple description and warning message in case of
+   a fixed parse buffer overflow.
+   @enddesc
+   @calls
+   @calledby
+   @history
+
+   @endhistory
+   @var     p
+   @vdesc   buffer location
+   @vtype   int
+   @vio     in
+   @vcomment
+
+   @endvar
+   @var     l
+   @vdesc   Line number
+   @vtype   int
+   @vio     in
+   @vcomment
+
+   @endvar
+
+@@*/
+
+static void CheckBuf(int p, int l)
+{
+  if (p >= BUF_SZ)
+  {
+    fprintf(stderr,"WARNING: Parser buffer overflow on line %d\n",
+            l);
+    fprintf(stderr,"This indicates either an incorrect parm file or\n");
+    fprintf(stderr,"the need to recompile " __FILE__ " with a bigger\n");
+    fprintf(stderr,"BUF_SZ parm.\n");
+
+    assert(0);
+    exit(1);
+  }
+}
+
+
+ /*@@
+   @routine removeSpaces
+   @author Paul Walker
+   @desc
+   removes the spaces from a char * <b>in place</b>. Beware
+   that this function will change the input value and if you
+   want to keep a copy you have to do so yourself!
+   @enddesc
+   @calls
+   @calledby
+   @history
+
+   @endvar
+   @var     stripMe
+   @vdesc   String to strip
+   @vtype   char *
+   @vio     inout
+   @vcomment
+
+   @endvar
+
+@@*/
+static void removeSpaces(char *stripMe)
+{
+  char *s;
+  unsigned int i,j;
+  s = (char *)malloc((strlen(stripMe)+2)*sizeof(char));
+
+  if(s)
+  {
+    strcpy(s,stripMe);
+    for (i=0,j=0;i<strlen(s);i++)
+    {
+      if (s[i] != ' ' && s[i] != '\t' && s[i] != '\n' && s[i] != '\r')
+      {
+        stripMe[j++] = s[i];
+      }
+      stripMe[j] = '\0';
+    }
+  }
+
+  free(s);
+}
+
+
+/* #define TEST_ParseFile */
+
+#ifdef TEST_ParseFile
+
+int parameter_printer(const char *param, const char *val)
+{
+  printf("Parameter %s has value %s\n", param, val);
+
+  return 0;
+}
+
+int main(int argc, char *argv[])
+{
+  int retval;
+  FILE *parameter_file;
+
+  if(argc > 1)
+  {
+    parameter_file = fopen(argv[1], "r");
+    if(parameter_file)
+    {
+      ParseFile(parameter_file, parameter_printer);
+      fclose(parameter_file);
+      retval = 0;
+    }
+    else
+    {
+      retval=2;
+    }
+  }
+  else
+  {
+    printf("Usage: %s <filename>\n", argv[0]);
+    retval = 1;
+  };
+
+  return 0;
+}
+
+#endif
+
+
+ /*@@
+   @routine ReadFile
+   @author Frank Loeffler
+   @desc
+   This routine reads a file into a buffer
+   @enddesc
+   @history
+   @var     file
+   @vdesc   The filestream to read
+   @vtype   FILE *
+   @vio     in
+   @vcomment
+
+   @endvar
+   @var     filesize
+   @vdesc   The size of the file
+   @vtype   *unsigned long
+   @vio     out
+   @vcomment
+
+   @endvar
+
+   @returntype char *
+   @returndesc
+   NULL - failure
+   !NULL allocated buffer
+   @endreturndesc
+@@*/
+static char *ReadFile(FILE *file, unsigned long *filesize)
+{
+  char *buffer;
+
+  if (!file)
+  {
+    fprintf(stderr, "Could not use file for reading.\n");
+    return NULL;
+  }
+  /* Get the file size */
+  fseek(file, 0, SEEK_END);
+  *filesize = ftell(file);
+  fseek(file, 0, SEEK_SET);
+  /* Allocate buffer */
+  buffer = (char *)malloc(*filesize+1);
+  if (!buffer)
+  {
+    fprintf(stderr, "Could not allocate memory.\n");
+    return NULL;
+  }
+  /* Read file into buffer and return */
+  fread(buffer, *filesize, 1, file);
+  /* Protect buffer for string operations */
+  buffer[*filesize] = '\0';
+  return buffer;
+}
+
+ /*@@
+   @routine ParseDefines
+   @author Frank Loeffler
+   @desc
+   This routine parses a buffer for defines of the form \$[^ \n] and
+   replaces them with some predefined defines, returning the new buffer,
+   which might be the same as the old buffer. Otherwise the old buffer
+   gets freed by this function. In case of parsing errors, the whole
+   parsing is stopped and the old buffer is returned
+   (FIXME: Should we return NULL?)
+   @enddesc
+   @history
+   @var     buffer
+   @vdesc   The buffer to parse
+   @vtype   char *
+   @vio     in
+   @vcomment
+
+   @endvar
+   @var     buffersize
+   @vdesc   The size of the buffer
+   @vtype   *unsigned long
+   @vio     out
+   @vcomment
+
+   @endvar
+
+   @returntype char *
+   @returndesc
+   !NULL - new buffer, might be == buffer
+   @endreturndesc
+@@*/
+static char *ParseDefines(char *buffer, unsigned long *buffersize)
+{
+  /* define name */
+  char define[1024];
+  /* Position in define name */
+  char defpos = 0;
+  /* Current position in buffer */
+  size_t pos = 0;
+  /* Character at current position */
+  char c;
+  /* Position of start of found define */
+  size_t def_start = 0;
+  /* Flag to indicate if we are inside a definition name */
+  int indef = 0;
+  if (!buffer)
+    return buffer;
+  /* Main loop over the buffer */
+  while (((c=buffer[pos]) != '\0') && (pos < *buffersize) )
+  {
+    /* Check if we found a define */
+    if (c == '$')
+    {
+      /* Mark the state and location and go on */
+      indef = 1;
+      def_start = pos;
+    }
+    /* If we are inside a define */
+    else if (indef)
+    {
+      /* Look for the end of the define name */
+      if (c == '}' || c == '\0' || c == '\n')
+      {
+        /* make the define name a proper string */
+        define[defpos] = '\0';
+        /* this holds the value of the define to be filled in */
+        char *value = NULL;
+        /* a new buffer for the whole thing */
+        char * new_buffer;
+        unsigned long new_size;
+        /* Check for different kinds of defines */
+        /* Environment variables */
+        if ((defpos > 6) &&
+            (strncmp(define, "ENV{'", 5) == 0) &&
+            (define[defpos-1] == '\''))
+        {
+          /* overwrite the trailing ' */
+          define[defpos-1] = '\0';
+          value = getenv(define+5);
+          if (!value)
+          {
+            CCTK_VWarn(CCTK_WARN_ALERT, __LINE__, __FILE__, CCTK_THORNSTRING,
+                       "No environment variable %s found\n", define+5);
+            /* TODO: Should we abort here? (return NULL) */
+          }
+          /* increase pos to jump over the trailing } */
+          if (pos+1 < *buffersize) { pos++; }
+        }
+        /* Parameter file name ? */
+        else if (strcmp(define, "parfile") == 0)
+        {
+          char path[500];
+          CCTK_ParameterFilename(500, path);
+          value = strrchr (path, '/');
+          if (value == NULL)
+          {
+            value = path;
+          }
+          else
+          {
+            value++;
+          }
+          /* skip the parameter file extension */
+          if (strcmp (value + strlen (value) - 4, ".par") == 0)
+          {
+            value[strlen (value) - 4] = '\0';
+          }
+        }
+        /* Else: unknown define - or no define at all: ignore */
+        if (value)
+        {
+          /* Replace the old buffer with the new, copying in all the data */
+          new_size = *buffersize - strlen(define) + strlen(value) + 1;
+          if (new_size < def_start)
+          {
+            CCTK_WARN(0, "Something is wrong with me, HELP!");
+            return buffer;
+          }
+          new_buffer = (char *)malloc(new_size);
+          if (!new_buffer)
+          {
+            CCTK_WARN(0, "I am out of memory and give up parsing for defines.");
+            return buffer;
+          }
+          new_buffer[0]='\0';
+          strncat(new_buffer, buffer, def_start);
+          strncat(new_buffer, value, new_size-1);
+          strncat(new_buffer, buffer+pos, new_size-1);
+          new_buffer[new_size-1] = '\0';
+          /* free the old buffer */
+          free(buffer);
+          /* Start further processing of new buffer */
+          pos = def_start + strlen(define);
+          buffer = new_buffer;
+          *buffersize = new_size;
+        }
+        /* General define cleanup */
+        indef = 0;
+        defpos = 0;
+        define[0] = '\0';
+        def_start = 0;
+      }
+      else if (defpos > 1023)
+      {
+        /* We only print this warning and ignore the possible define problem.
+         * It might not be a define after all but a valid, long parameter
+         * value containing a '$'.*/
+        define[1023] = '\0';
+        CCTK_VWarn(CCTK_WARN_PICKY, __LINE__, __FILE__, CCTK_THORNSTRING,
+                   "Possible define too long: %s", define);
+        indef = 0;
+        defpos = 0;
+        define[0] = '\0';
+        def_start = 0;
+      }
+      else
+        define[defpos++] = c;
+    }
+    pos++;
+  }
+  return buffer;
+}
+
+ /*@@
+   @routine ParseBuffer
+   @author Paul Walker
+   @desc
+   This routine actually parses the parameter file. The
+   syntax we allow is
+   <ul>
+     <li>a = b
+         <li>a,b,c = d,e,f
+         <li># rest of the line is ignored
+         <li>x = "string value"
+   </ul>
+   So it is easy to parse
+   <p>
+   We go through the file looking for stuff and then set
+   it in the global database using calls to the passed in set_function.
+   @enddesc
+   @history
+   @hdate Tue Jan 12 16:41:36 1999 @hauthor Tom Goodale
+   @hdesc Moved to CCTK.
+          Changed to pass data to arbitrary function.
+          Changed to take a file descriptor rather than a filename.
+          Use a buffer to parse which can be preprocessed before main parsing
+   @endhistory
+   @var     buffer
+   @vdesc   The buffer to parse
+   @vtype   char *
+   @vio     in
+   @vcomment
+
+   @endvar
+   @var     set_function
+   @vdesc   The function to call to set the value of a parameter
+   @vtype   int (*)(const char *, const char *)
+   @vio     in
+   @vcomment
+
+   @endvar
+   @var     ConfigData
+   @vdesc   Flesh configuration data
+   @vtype   tFleshConfig *
+   @vio     in
+   @vcomment
+
+   @endvar
+
+   @returntype int
+   @returndesc
+   0 - success
+   @endreturndesc
+@@*/
+int ParseBuffer(char *buffer,
+              int (*set_function)(const char *, const char *, int),
+              tFleshConfig *ConfigData)
+{
+  /* position in buffer */
+  unsigned int pos = 0;
   /* Buffers for parsing from the file */
   char *tokens, *value;
   char *subtoken, *subvalue;
@@ -122,10 +554,8 @@ int ParseFile(FILE *ifp,
   int ntokens;
   /* Status flags */
   int intoken, inval;
-  /* Current char. Have to make it an int so we can compare with
-     EOF. See man 3 fgetc
-   */
-  int c;
+  /* Current char */
+  char c;
   int num_errors; /* number of errors in file parsing */
 
   num_errors = 0;
@@ -141,7 +571,7 @@ int ParseFile(FILE *ifp,
 
   intoken = 0; inval = 0;
 
-  while ((c=fgetc(ifp)) != EOF)
+  while ((c=buffer[pos++]) != '\0')
   {
 #ifdef DEBUG
     printf("%c",c);
@@ -150,7 +580,7 @@ int ParseFile(FILE *ifp,
     while (c == '#' || c == '!' )
     {
       /* Comment line.  So forget rest of line */
-      while ((c=fgetc(ifp)) != '\n' && c != '\r' && c != EOF)
+      while ((c=buffer[pos++]) != '\n' && c != '\r' && c != '\0')
       {
 #ifdef DEBUG
         printf("%c",c);
@@ -160,7 +590,7 @@ int ParseFile(FILE *ifp,
       {
         lineno++;
       }
-      c = fgetc(ifp);
+      c = buffer[pos++];
 #ifdef DEBUG
       printf("%c",c);
 #endif
@@ -220,7 +650,7 @@ int ParseFile(FILE *ifp,
          * and check if the value is a string or not.
          * This parser DOES strip quotes off of the strings.
          */
-        while ((c = fgetc(ifp)) == ' ' || c == '\n' || c == '\r' || c == '\t')
+        while ((c = buffer[pos++]) == ' ' || c == '\n' || c == '\r' || c == '\t')
         {
 #ifdef DEBUG
           printf("%c",c);
@@ -251,7 +681,7 @@ int ParseFile(FILE *ifp,
             free (tokens);
             return 1;
           }
-          while ((c = fgetc(ifp)) != '"')
+          while ((c = buffer[pos++]) != '"')
           {
 #ifdef DEBUG
             printf("%c",c);
@@ -265,7 +695,7 @@ int ParseFile(FILE *ifp,
 #endif
               lineno++;
             }
-            else if (c == EOF)
+            else if (c == '\0')
             {
               break;
             }
@@ -274,9 +704,9 @@ int ParseFile(FILE *ifp,
           if (c == '"')
           {
             int is_comment = 0;
-            while ((c = fgetc(ifp)) != '\n')
+            while ((c = buffer[pos++]) != '\n')
             {
-              if (c == EOF)
+              if (c == '\0')
               {
                 break;
               }
@@ -295,7 +725,7 @@ int ParseFile(FILE *ifp,
                 return 1;
               }
             }
-            if (c == '\n' || c == EOF)
+            if (c == '\n' || c == '\0')
             {
               if (c == '\n') lineno++;
               /* mark it as properly quoted string value */
@@ -319,39 +749,6 @@ int ParseFile(FILE *ifp,
 #endif
           set_function(tokens,value, lineno);
         }
-        else if (c == '$')
-        {
-          /* We got a define */
-          /* FIXME: Assume it is a parameter file for now */
-          char path[500];
-          char *parfile;
-
-          CCTK_ParameterFilename(500,path);
-          parfile = strrchr (path, '/');
-          if (parfile == NULL)
-          {
-            parfile = path;
-          }
-          else
-          {
-            parfile++;
-          }
-          /* skip the parameter file extension */
-          if (strcmp (parfile + strlen (parfile) - 4, ".par") == 0)
-          {
-            parfile[strlen (parfile) - 4] = 0;
-          }
-
-          /* ignore everything else on the line */
-          while (!(c==' ' || c=='\t' || c == '\n' || c == '\r' || c == EOF))
-          {
-            c = fgetc(ifp);
-#ifdef DEBUG
-            printf("%c",c);
-#endif
-          }
-          set_function(tokens,parfile,lineno);
-        }
         else
         {
 
@@ -362,15 +759,15 @@ int ParseFile(FILE *ifp,
             /* Simple case. We have an int
                or a double which contain no
                spaces! */
-            c = fgetc(ifp);
+            c = buffer[pos++];
 #ifdef DEBUG
             printf("%c",c);
 #endif
-            while (!(c==' ' || c=='\t' || c == '\n' || c == '\r' || c == EOF))
+            while (!(c==' ' || c=='\t' || c == '\n' || c == '\r' || c == '\0'))
             {
               value[p++] = (char)c;
               CheckBuf(p,lineno);
-              c = fgetc(ifp);
+              c = buffer[pos++];
 #ifdef DEBUG
               printf("%c",c);
 #endif
@@ -402,11 +799,11 @@ int ParseFile(FILE *ifp,
                ntokens-1 commas, stripping spaces, and
                make a nice little string.
                */
-            c = fgetc(ifp);
+            c = buffer[pos++];
 #ifdef DEBUG
             printf("%c",c);
 #endif
-            while (ncommas < ntokens-1 && c != EOF)
+            while (ncommas < ntokens-1 && c != '\0')
             {
               if (!(c == ' ' || c == '\t' || c == '\n' || c == '\r'))
               {
@@ -414,7 +811,7 @@ int ParseFile(FILE *ifp,
                 CheckBuf(pp,lineno);
               }
               if (c == ',') ncommas ++;
-              c = fgetc(ifp);
+              c = buffer[pos++];
 #ifdef DEBUG
               printf("%c",c);
 #endif
@@ -422,7 +819,7 @@ int ParseFile(FILE *ifp,
             if (c == ' ' || c == '\t')
             {
               /* Great now strip out the spaces */
-              while((c = fgetc(ifp)) == ' ' || c=='\t' || c == '\n' || c == '\r')
+              while((c = buffer[pos++]) == ' ' || c=='\t' || c == '\n' || c == '\r')
               {
 #ifdef DEBUG
                 printf("%c",c);
@@ -441,15 +838,15 @@ int ParseFile(FILE *ifp,
             value[pp++] = (char)c;
             CheckBuf(p,lineno);
 
-            c = fgetc(ifp);
+            c = buffer[pos++];
 #ifdef DEBUG
             printf("%c",c);
 #endif
-            while (c != ' ' && c != '\t' && c != '\n' && c != '\r' && c != EOF)
+            while (c != ' ' && c != '\t' && c != '\n' && c != '\r' && c != '\0')
             {
               value[pp++] = (char)c;
               CheckBuf(pp,lineno);
-              c = fgetc(ifp);
+              c = buffer[pos++];
 #ifdef DEBUG
               printf("%c",c);
 #endif
@@ -525,137 +922,3 @@ int ParseFile(FILE *ifp,
   return num_errors;
 }
 
-/********************************************************************
- *********************     Local Routines   *************************
- ********************************************************************/
-
- /*@@
-   @routine CheckBuf
-   @author Paul Walker
-   @desc
-   A simple description and warning message in case of
-   a fixed parse buffer overflow.
-   @enddesc
-   @calls
-   @calledby
-   @history
-
-   @endhistory
-   @var     p
-   @vdesc   buffer location
-   @vtype   int
-   @vio     in
-   @vcomment
-
-   @endvar
-   @var     l
-   @vdesc   Line number
-   @vtype   int
-   @vio     in
-   @vcomment
-
-   @endvar
-
-@@*/
-
-static void CheckBuf(int p, int l)
-{
-  if (p >= BUF_SZ)
-  {
-    fprintf(stderr,"WARNING: Parser buffer overflow on line %d\n",
-            l);
-    fprintf(stderr,"This indicates either an incorrect parm file or\n");
-    fprintf(stderr,"the need to recompile " __FILE__ " with a bigger\n");
-    fprintf(stderr,"BUF_SZ parm.\n");
-
-    assert(0);
-    exit(1);
-  }
-}
-
-
- /*@@
-   @routine removeSpaces
-   @author Paul Walker
-   @desc
-   removes the spaces from a char * <b>in place</b>. Beware
-   that this function will change the input value and if you
-   want to keep a copy you have to do so yourself!
-   @enddesc
-   @calls
-   @calledby
-   @history
-
-   @endvar
-   @var     stripMe
-   @vdesc   String to strip
-   @vtype   char *
-   @vio     inout
-   @vcomment
-
-   @endvar
-
-@@*/
-static void removeSpaces(char *stripMe)
-{
-  char *s;
-  unsigned int i,j;
-  s = (char *)malloc((strlen(stripMe)+2)*sizeof(char));
-
-  if(s)
-  {
-    strcpy(s,stripMe);
-    for (i=0,j=0;i<strlen(s);i++)
-    {
-      if (s[i] != ' ' && s[i] != '\t' && s[i] != '\n' && s[i] != '\r')
-      {
-        stripMe[j++] = s[i];
-      }
-      stripMe[j] = '\0';
-    }
-  }
-
-  free(s);
-}
-
-
-/* #define TEST_ParseFile */
-
-#ifdef TEST_ParseFile
-
-int parameter_printer(const char *param, const char *val)
-{
-  printf("Parameter %s has value %s\n", param, val);
-
-  return 0;
-}
-
-int main(int argc, char *argv[])
-{
-  int retval;
-  FILE *parameter_file;
-
-  if(argc > 1)
-  {
-    parameter_file = fopen(argv[1], "r");
-    if(parameter_file)
-    {
-      ParseFile(parameter_file, parameter_printer);
-      fclose(parameter_file);
-      retval = 0;
-    }
-    else
-    {
-      retval=2;
-    }
-  }
-  else
-  {
-    printf("Usage: %s <filename>\n", argv[0]);
-    retval = 1;
-  };
-
-  return 0;
-}
-
-#endif