When compiling format strings, nmh attempts to avoid multiple parsing

of address and date fields by only inserting calls to the parse
functions (FT_PARSEADDR and FT_PARSEDATE) for a given component once.
The problem with this method is that the initial invocation may
actually be on a code path that is conditionally executed.  This can
result cached copies of data from the fields in previous messages to
be used.

My solution is to move this optimization from compile time to run time.
Address and Date parsing calls (FT_PARSEADDR and FT_PARSEDATE) will
always be included.  Run time flags are used to prevent these functions
from being run more than once per component per message.

The c_flags field has being converted from a boolean to a bit-field to
facilitate maintenance of the new CT_PARSED value.  The result value
that used to be in this field is now the bit CF_TRUE and the
overloaded use of this field by scan() is now the CT_DATEFAB bit.

Some unneeded flags (CT_ADDRPARSE, CT_MYMBOX) have also been removed.

diff --git a/ChangeLog b/ChangeLog
index b0a7242..2ba6be3 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,12 @@
+2003-08-10  Jeffrey C Honig  <jch@honig.net>
+
+       * Fix problem where parsing of address/date fields in fmt_compile
+       is optimized to the first instance.  The first instance may be in
+       contitional code which will result in cached data to
+       be used.  Instead, convert c_flags to a flags field from a boolean
+       and parse on the first use.
+       * Remove some unused flag bits.
+
 Fri Jul 01 22:02:00 2003 Glenn Burkhardt <glenn@aoi-industries.com>
 
        * Applied fixes for configuration problems with Solaris and

diff --git a/h/fmt_scan.h b/h/fmt_scan.h
index fd4c555..cece50e 100644 (file)
--- a/h/fmt_scan.h
+++ b/h/fmt_scan.h
@@ -34,8 +34,13 @@ struct comp {
  */
 #define        CT_ADDR       (1<<0)    /* referenced as address    */
 #define        CT_DATE       (1<<1)    /* referenced as date       */
-#define        CT_MYMBOX     (1<<2)    /* "mymbox" test being done */
-#define        CT_ADDRPARSE  (1<<3)    /* address parse being done */
+
+/*
+ * c_flags bits
+ */
+#define        CF_TRUE       (1<<0)    /* usually means component is present */
+#define        CF_PARSED     (1<<1)    /* address/date has been parsed */
+#define        CF_DATEFAB    (1<<2)    /* datefield fabricated */
 
 extern int fmt_norm;
 

diff --git a/sbr/fmt_compile.c b/sbr/fmt_compile.c
index 4c64b9c..a478acb 100644 (file)
--- a/sbr/fmt_compile.c
+++ b/sbr/fmt_compile.c
@@ -423,13 +423,11 @@ do_name(char *sp, int preprocess)
        if (cm->c_type & CT_ADDR) {
            CERROR("component used as both date and address");
        }
-       if (! (cm->c_type & CT_DATE)) {
-           cm->c_tws = (struct tws *)
-                               calloc((size_t) 1, sizeof(*cm->c_tws));
-           fp->f_type = preprocess;
-           PUTCOMP(sp);
-           cm->c_type |= CT_DATE;
-       }
+       cm->c_tws = (struct tws *)
+           calloc((size_t) 1, sizeof(*cm->c_tws));
+       fp->f_type = preprocess;
+       PUTCOMP(sp);
+       cm->c_type |= CT_DATE;
        break;
 
     case FT_MYMBOX:
@@ -437,18 +435,15 @@ do_name(char *sp, int preprocess)
            ismymbox ((struct mailname *) 0);
            primed++;
        }
-       cm->c_type |= CT_MYMBOX;
        /* fall through */
     case FT_PARSEADDR:
        if (cm->c_type & CT_DATE) {
            CERROR("component used as both date and address");
        }
-       if (! (cm->c_type & CT_ADDRPARSE)) {
-           cm->c_mn = &fmt_mnull;
-           fp->f_type = preprocess;
-           PUTCOMP(sp);
-           cm->c_type |= (CT_ADDR | CT_ADDRPARSE);
-       }
+       cm->c_mn = &fmt_mnull;
+       fp->f_type = preprocess;
+       PUTCOMP(sp);
+       cm->c_type |= CT_ADDR;
        break;
 
     case FT_FORMATADDR:

diff --git a/sbr/fmt_scan.c b/sbr/fmt_scan.c
index 5dc7f22..0a2397b 100644 (file)
--- a/sbr/fmt_scan.c
+++ b/sbr/fmt_scan.c
@@ -296,6 +296,15 @@ fmt_scan (struct format *format, char *scanl, int width, int *dat)
 
     cp = scanl;
     ep = scanl + width - 1;
+
+    for (fmt = format; fmt->f_type != FT_DONE; fmt++)
+       switch (fmt->f_type) {
+       case FT_PARSEADDR:
+       case FT_PARSEDATE:
+           fmt->f_comp->c_flags &= ~CF_PARSED;
+           break;
+       }
+
     fmt = format;
 
     while (cp < ep) {
@@ -490,7 +499,7 @@ fmt_scan (struct format *format, char *scanl, int width, int *dat)
            break;
 
        case FT_LV_COMPFLAG:
-           value = fmt->f_comp->c_flags;
+           value = (fmt->f_comp->c_flags & CF_TRUE) != 0;
            break;
        case FT_LV_COMP:
            value = (comp = fmt->f_comp)->c_text ? atoi(comp->c_text) : 0;
@@ -710,13 +719,16 @@ fmt_scan (struct format *format, char *scanl, int width, int *dat)
 
        case FT_PARSEDATE:
            comp = fmt->f_comp;
+           if (comp->c_flags & CF_PARSED)
+               break;
            if ((sp = comp->c_text) && (tws = dparsetime(sp))) {
                *comp->c_tws = *tws;
-               comp->c_flags = 0;
-           } else if (comp->c_flags >= 0) {
+               comp->c_flags &= ~CF_TRUE;
+           } else if ((comp->c_flags & CF_DATEFAB) == 0) {
                memset ((char *) comp->c_tws, 0, sizeof *comp->c_tws);
-               comp->c_flags = 1;
+               comp->c_flags = CF_TRUE;
            }
+           comp->c_flags |= CF_PARSED;
            break;
 
        case FT_FORMATADDR:
@@ -779,6 +791,8 @@ fmt_scan (struct format *format, char *scanl, int width, int *dat)
 
        case FT_PARSEADDR:
            comp = fmt->f_comp;
+           if (comp->c_flags & CF_PARSED)
+               break;
            if (comp->c_mn != &fmt_mnull)
                mnfree (comp->c_mn);
            if ((sp = comp->c_text) && (sp = getname(sp)) &&
@@ -786,6 +800,7 @@ fmt_scan (struct format *format, char *scanl, int width, int *dat)
                comp->c_mn = mn;
                while (getname(""))
                    ;
+               comp->c_flags |= CF_PARSED;
            } else {
                while (getname(""))             /* XXX */
                    ;
@@ -805,15 +820,22 @@ fmt_scan (struct format *format, char *scanl, int width, int *dat)
            if ((sp = comp->c_text) && (sp = getname(sp)) &&
                (mn = getm (sp, NULL, 0, AD_NAME, NULL))) {
                comp->c_mn = mn;
-               comp->c_flags = ismymbox(mn);
+               if (ismymbox(mn))
+                   comp->c_flags |= CF_TRUE;
+               else
+                   comp->c_flags &= ~CF_TRUE;
                while ((sp = getname(sp)))
-                   if (comp->c_flags == 0 &&
+                   if ((comp->c_flags & CF_TRUE) == 0 &&
                        (mn = getm (sp, NULL, 0, AD_NAME, NULL)))
-                       comp->c_flags |= ismymbox(mn);
+                       if (ismymbox(mn))
+                           comp->c_flags |= CF_TRUE;
            } else {
                while (getname(""))             /* XXX */
                    ;
-               comp->c_flags = (comp->c_text == 0);
+               if (comp->c_text == 0)
+                   comp->c_flags |= CF_TRUE;
+               else
+                   comp->c_flags &= ~CF_TRUE;
                comp->c_mn = &fmt_mnull;
            }
            break;

diff --git a/uip/fmtdump.c b/uip/fmtdump.c
index cc0bc70..cc9a589 100644 (file)
--- a/uip/fmtdump.c
+++ b/uip/fmtdump.c
@@ -39,6 +39,7 @@ static int findlabel(struct format *);
 static void assignlabel(struct format *);
 static char *f_typestr(int);
 static char *c_typestr(int);
+static char *c_flagsstr(int);
 static void litputs(char *);
 static void litputc(char);
 
@@ -163,7 +164,7 @@ dumpone(struct format *fmt)
                if (fmt->f_comp->c_type)
                        printf(", c_type %s", c_typestr(fmt->f_comp->c_type));
                if (fmt->f_comp->c_flags)
-                       printf(", c_flags %d", fmt->f_comp->c_flags);
+                       printf(", c_flags %s", c_flagsstr(fmt->f_comp->c_flags));
                break;
 
        case FT_LV_SEC:
@@ -195,7 +196,7 @@ dumpone(struct format *fmt)
                if (fmt->f_comp->c_type)
                        printf(", c_type %s", c_typestr(fmt->f_comp->c_type));
                if (fmt->f_comp->c_flags)
-                       printf(", c_flags %d", fmt->f_comp->c_flags);
+                       printf(", c_flags %s", c_flagsstr(fmt->f_comp->c_flags));
                break;
 
        case FT_LS_ADDR:
@@ -217,7 +218,7 @@ dumpone(struct format *fmt)
                if (fmt->f_comp->c_type)
                        printf(", c_type %s", c_typestr(fmt->f_comp->c_type));
                if (fmt->f_comp->c_flags)
-                       printf(", c_flags %d", fmt->f_comp->c_flags);
+                       printf(", c_flags %s", c_flagsstr(fmt->f_comp->c_flags));
                break;
 
        case FT_COMPF:
@@ -228,7 +229,7 @@ dumpone(struct format *fmt)
                if (fmt->f_comp->c_type)
                        printf(", c_type %s", c_typestr(fmt->f_comp->c_type));
                if (fmt->f_comp->c_flags)
-                       printf(", c_flags %d", fmt->f_comp->c_flags);
+                       printf(", c_flags %s", c_flagsstr(fmt->f_comp->c_flags));
                break;
 
        case FT_STRF:
@@ -452,19 +453,35 @@ c_typestr(int t)
        static char buf[64];
 
        buf[0] = '\0';
-       if (t & ~(CT_ADDR|CT_DATE|CT_MYMBOX|CT_ADDRPARSE))
+       if (t & ~(CT_ADDR|CT_DATE))
                printf(buf, "0x%x ", t);
        strcat(buf, "<");
        i = 0;
        FNORD(CT_ADDR, "ADDR");
        FNORD(CT_DATE, "DATE");
-       FNORD(CT_MYMBOX, "MYMBOX");
-       FNORD(CT_ADDRPARSE, "ADDRPARSE");
        strcat(buf, ">");
        return(buf);
-#undef FNORD
 }
 
+static char *
+c_flagsstr(int t)
+{
+       register int i;
+       static char buf[64];
+
+       buf[0] = '\0';
+       if (t & ~(CF_TRUE|CF_PARSED|CF_DATEFAB))
+               printf(buf, "0x%x ", t);
+       strcat(buf, "<");
+       i = 0;
+       FNORD(CF_TRUE, "TRUE");
+       FNORD(CF_PARSED, "PARSED");
+       FNORD(CF_DATEFAB, "DATEFAB");
+       strcat(buf, ">");
+       return(buf);
+}
+#undef FNORD
+
 static void
 litputs(char *s)
 {

diff --git a/uip/scansbr.c b/uip/scansbr.c
index c04e8c7..be68bf8 100644 (file)
--- a/uip/scansbr.c
+++ b/uip/scansbr.c
@@ -331,9 +331,9 @@ finished:
                if (datecomp->c_tws == NULL)
                    adios (NULL, "unable to allocate tws buffer");
                *datecomp->c_tws = *dlocaltime ((time_t *) &st.st_mtime);
-               datecomp->c_flags = -1;
+               datecomp->c_flags |= CF_DATEFAB|CF_TRUE;
            } else {
-               datecomp->c_flags = 0;
+               datecomp->c_flags &= ~CF_DATEFAB;
            }
        }
     }