[PATCH] Simplify date handling and make it more reliable

This make all dates be stores as seconds since UTC epoch, with 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 :)

commit-tree now eats RFC2822 dates as AUTHOR_DATE because that's
what you're going to want to feed it.

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

2 files changed, 165 insertions, 6 deletions

diff --git a/commit-tree.c b/commit-tree.c
index ac431febe9..50fe19652f 100644
--- a/commit-tree.c
+++ b/commit-tree.c
@@ -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 void remove_special(char *p)
 	}
 }
 
+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; i<7; 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; i<12; 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 @@ int main(int argc, char **argv)
 	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 @@ int main(int argc, char **argv)
 	realemail[len] = '@';
 	gethostname(realemail+len+1, sizeof(realemail)-len-1);
 	time(&now);
-	realdate = ctime(&now);
+	tm = localtime(&now);
+
+	strftime(realdate, sizeof(realdate), "%s %z", tm);
+	strcpy(date, realdate);
 
 	gecos = getenv("AUTHOR_NAME") ? : realgecos;
 	email = getenv("AUTHOR_EMAIL") ? : realemail;
-	date = getenv("AUTHOR_DATE") ? : realdate;
+	audate = getenv("AUTHOR_DATE");
+	if (audate)
+		parse_rfc2822_date(audate, date, sizeof(date));
 
 	remove_special(gecos); remove_special(realgecos);
 	remove_special(email); remove_special(realemail);
-	remove_special(date); remove_special(realdate);
 
 	init_buffer(&buffer, &size);
 	add_buffer(&buffer, &size, "tree %s\n", sha1_to_hex(tree_sha1));
diff --git a/rev-tree.c b/rev-tree.c
index d3fc93c61a..33caac3d03 100644
--- a/rev-tree.c
+++ b/rev-tree.c
@@ -1,4 +1,5 @@
 #define _XOPEN_SOURCE /* glibc2 needs this */
+#define _BSD_SOURCE /* for tm.tm_gmtoff */
 #include <time.h>
 #include <ctype.h>
 
@@ -21,6 +22,7 @@ static unsigned long parse_time(const char *buf)
 	char buffer[100];
 	struct tm tm;
 	const char *formats[] = {
+		"%s",
 		"%c",
 		"%a %b %d %T %y",
 		NULL
@@ -30,7 +32,7 @@ static unsigned long parse_time(const char *buf)
 	p = buffer;
 	while (isspace(c = *buf))
 		buf++;
-	while ((c = *buf++) != '\n')
+	while ((c = *buf++) != '\n' && c)
 		*p++ = c;
 	*p++ = 0;
 	buf = buffer;
@@ -50,6 +52,8 @@ static unsigned long parse_time(const char *buf)
 
 static unsigned long parse_commit_date(const char *buf)
 {
+	unsigned long time;
+
 	if (memcmp(buf, "author", 6))
 		return 0;
 	while (*buf++ != '\n')
@@ -58,7 +62,11 @@ static unsigned long parse_commit_date(const char *buf)
 		return 0;
 	while (*buf++ != '>')
 		/* nada */;
-	return parse_time(buf);
+
+	time = strtoul(buf, NULL, 10);
+	if (!time)
+		time = parse_time(buf);
+	return time;
 }
 
 static int parse_commit(unsigned char *sha1)