Re: Date handling.

2005-04-14 Thread David Woodhouse
On Thu, 2005-04-14 at 02:12 -0700, Linus Torvalds wrote:
 I take that back. I'd be much happier with you doing and testing it, 
 because now I'm crashing.

OK. commit-tree now eats RFC2822 dates as AUTHOR_DATE because that's
what you're going to want to feed it. We store seconds since UTC epoch,
we add the author's or committer's timezone as auxiliary data so that
dates can be pretty-printed in the original timezone later if anyone
cares. I left the date parsing in rev-tree.c for backward compatibility
but it can be dropped when we change to base64 :)

Yes, glibc sucks and strptime is a pile of crap. We have to parse it
ourselves.

Index: commit-tree.c
--- 1756b578489f93999ded68ae347bef7d6063101c/commit-tree.c  (mode:100664 
sha1:12196c79f31d004dff0df1f50dda67d8204f5568)
+++ 82ba574c85e9a2e4652419c88244e9dd1bfa8baa/commit-tree.c  (mode:100644 
sha1:35cb09402c9868499bcaf6de42afbad9fdfebe05)
@@ -7,6 +7,9 @@
 
 #include pwd.h
 #include time.h
+#include string.h
+#include ctype.h
+#include time.h
 
 #define BLOCKING (1ul  14)
 #define ORIG_OFFSET (40)
@@ -95,6 +98,148 @@
}
 }
 
+static const char *month_names[] = {
+Jan, Feb, Mar, Apr, May, Jun,
+Jul, Aug, Sep, Oct, Nov, Dec
+};
+
+static const char *weekday_names[] = {
+Sun, Mon, Tue, Wed, Thu, Fri, Sat
+};
+
+
+static char *skipfws(char *str)
+{
+   while (isspace(*str))
+   str++;
+   return str;
+}
+
+   
+/* Gr. strptime is crap for this; it doesn't have a way to require RFC2822
+   (i.e. English) day/month names, and it doesn't work correctly with %z. */
+static void parse_rfc2822_date(char *date, char *result, int maxlen)
+{
+   struct tm tm;
+   char *p;
+   int i, offset;
+   time_t then;
+
+   memset(tm, 0, sizeof(tm));
+
+   /* Skip day-name */
+   p = skipfws(date);
+   if (!isdigit(*p)) {
+   for (i=0; i7; i++) {
+   if (!strncmp(p,weekday_names[i],3)  p[3] == ',') {
+   p = skipfws(p+4);
+   goto day;
+   }
+   }
+   return;
+   }   
+
+   /* day */
+ day:
+   tm.tm_mday = strtoul(p, p, 10);
+
+   if (tm.tm_mday  1 || tm.tm_mday  31)
+   return;
+
+   if (!isspace(*p))
+   return;
+
+   p = skipfws(p);
+
+   /* month */
+
+   for (i=0; i12; i++) {
+   if (!strncmp(p, month_names[i], 3)  isspace(p[3])) {
+   tm.tm_mon = i;
+   p = skipfws(p+strlen(month_names[i]));
+   goto year;
+   }
+   }
+   return; /* Error -- bad month */
+
+   /* year */
+ year: 
+   tm.tm_year = strtoul(p, p, 10);
+
+   if (!tm.tm_year  !isspace(*p))
+   return;
+
+   if (tm.tm_year  1900)
+   tm.tm_year -= 1900;
+   
+   p=skipfws(p);
+
+   /* hour */
+   if (!isdigit(*p))
+   return;
+   tm.tm_hour = strtoul(p, p, 10);
+   
+   if (!tm.tm_hour  23)
+   return;
+
+   if (*p != ':')
+   return; /* Error -- bad time */
+   p++;
+
+   /* minute */
+   if (!isdigit(*p))
+   return;
+   tm.tm_min = strtoul(p, p, 10);
+   
+   if (!tm.tm_min  59)
+   return;
+
+   if (isspace(*p))
+   goto zone;
+
+   if (*p != ':')
+   return; /* Error -- bad time */
+   p++;
+
+   /* second */
+   if (!isdigit(*p))
+   return;
+   tm.tm_sec = strtoul(p, p, 10);
+   
+   if (!tm.tm_sec  59)
+   return;
+
+   if (!isspace(*p))
+   return;
+
+ zone:
+   p = skipfws(p);
+
+   if (*p == '-')
+   offset = -60;
+   else if (*p == '+')
+   offset = 60;
+   else
+  return;
+
+   if (!isdigit(p[1]) || !isdigit(p[2]) || !isdigit(p[3]) || 
!isdigit(p[4]))
+   return;
+
+   i = strtoul(p+1, NULL, 10);
+   offset *= ((i % 100) + ((i / 100) * 60));
+
+   if (*(skipfws(p + 5)))
+   return;
+
+   then = mktime(tm); /* mktime appears to ignore the GMT offset, 
stupidly */
+   if (then == -1)
+   return;
+
+   then -= offset;
+
+   snprintf(result, maxlen, %lu %5.5s, then, p);
+}
+
 /*
  * Having more than two parents may be strange, but hey, there's
  * no conceptual reason why the file format couldn't accept multi-way
@@ -114,10 +259,12 @@
unsigned char commit_sha1[20];
char *gecos, *realgecos;
char *email, realemail[1000];
-   char *date, *realdate;
+   char date[20], realdate[20];
+   char *audate;
char comment[1000];
struct passwd *pw;
time_t now;
+   struct tm *tm;
char *buffer;
unsigned int size;
 
@@ -142,15 +289,19 @@
realemail[len] = '@';
   

Re: Date handling.

2005-04-14 Thread David Woodhouse
On Thu, 2005-04-14 at 12:19 -0700, [EMAIL PROTECTED] wrote:
 With a UTC date, why would anyone care in which timezone the commit was
 made?  Any pretty printing would most likely be prettiest if it is done
 relative to the timezone of the person looking at the commit record, not
 the person who created the record.

I'd prefer not to lose the information. If someone has committed a
change at 2am, I like to know that it was 2am for _them_. It helps me
decide where to look first for the cause of problems. :)

It also helps disambiguate certain comments, especially those involving
words or phrases such as yesterday or this afternoon.

-- 
dwmw2


-
To unsubscribe from this list: send the line unsubscribe git in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html


RE: Date handling.

2005-04-14 Thread Luck, Tony
I'd prefer not to lose the information. If someone has committed a
change at 2am, I like to know that it was 2am for _them_. It helps me
decide where to look first for the cause of problems. :)

I'd think the 8:00am-before-the-first-coffee checkins would be the
most worrying :-)

It also helps disambiguate certain comments, especially those involving
words or phrases such as yesterday or this afternoon.

This is a very good point ... but this still has problems with the
git is a filesystem, not a SCM mantra.  Timezone comments don't
belong in the git inode.

-Tony
-
To unsubscribe from this list: send the line unsubscribe git in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html