git-commit-vandalism/commit-tree.c

/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
#include "cache.h"

#include <pwd.h>
#include <time.h>
#include <string.h>
#include <ctype.h>
#include <time.h>

#define BLOCKING (1ul << 14)
#define ORIG_OFFSET (40)

/*
 * Leave space at the beginning to insert the tag
 * once we know how big things are.
 *
 * FIXME! Share the code with "write-tree.c"
 */
static void init_buffer(char **bufp, unsigned int *sizep)
{
	char *buf = malloc(BLOCKING);
	memset(buf, 0, ORIG_OFFSET);
	*sizep = ORIG_OFFSET;
	*bufp = buf;
}

static void add_buffer(char **bufp, unsigned int *sizep, const char *fmt, ...)
{
	char one_line[2048];
	va_list args;
	int len;
	unsigned long alloc, size, newsize;
	char *buf;

	va_start(args, fmt);
	len = vsnprintf(one_line, sizeof(one_line), fmt, args);
	va_end(args);
	size = *sizep;
	newsize = size + len;
	alloc = (size + 32767) & ~32767;
	buf = *bufp;
	if (newsize > alloc) {
		alloc = (newsize + 32767) & ~32767;
		buf = realloc(buf, alloc);
		*bufp = buf;
	}
	*sizep = newsize;
	memcpy(buf + size, one_line, len);
}

static int prepend_integer(char *buffer, unsigned val, int i)
{
	buffer[--i] = '\0';
	do {
		buffer[--i] = '0' + (val % 10);
		val /= 10;
	} while (val);
	return i;
}

static void finish_buffer(char *tag, char **bufp, unsigned int *sizep)
{
	int taglen;
	int offset;
	char *buf = *bufp;
	unsigned int size = *sizep;

	offset = prepend_integer(buf, size - ORIG_OFFSET, ORIG_OFFSET);
	taglen = strlen(tag);
	offset -= taglen;
	buf += offset;
	size -= offset;
	memcpy(buf, tag, taglen);

	*bufp = buf;
	*sizep = size;
}

static void remove_special(char *p)
{
	char c;
	char *dst = p, *src = p;

	for (;;) {
		c = *src;
		src++;
		switch(c) {
		case '\n': case '<': case '>':
			continue;
		}
		*dst++ = c;
		if (!c)
			break;
	}

	/*
	 * Go back, and remove crud from the end: some people
	 * have commas etc in their gecos field
	 */
	dst--;
	while (--dst >= p) {
		unsigned char c = *dst;
		switch (c) {
		case ',': case ';': case '.':
			*dst = 0;
			continue;
		}
		break;
	}
}

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);
}

static void check_valid(unsigned char *sha1, const char *expect)
{
	void *buf;
	char type[20];
	unsigned long size;

	buf = read_sha1_file(sha1, type, &size);
	if (!buf || strcmp(type, expect))
		die("%s is not a valid '%s' object", sha1_to_hex(sha1), expect);
	free(buf);
}

/*
 * Having more than two parents may be strange, but hey, there's
 * no conceptual reason why the file format couldn't accept multi-way
 * merges. It might be the "union" of several packages, for example.
 *
 * I don't really expect that to happen, but this is here to make
 * it clear that _conceptually_ it's ok..
 */
#define MAXPARENT (16)

int main(int argc, char **argv)
{
	int i, len;
	int parents = 0;
	unsigned char tree_sha1[20];
	unsigned char parent_sha1[MAXPARENT][20];
	unsigned char commit_sha1[20];
	char *gecos, *realgecos, *commitgecos;
	char *email, *commitemail, realemail[1000];
	char date[20], realdate[20];
	char *audate;
	char comment[1000];
	struct passwd *pw;
	time_t now;
	struct tm *tm;
	char *buffer;
	unsigned int size;

	if (argc < 2 || get_sha1_hex(argv[1], tree_sha1) < 0)
		usage("commit-tree <sha1> [-p <sha1>]* < changelog");

	check_valid(tree_sha1, "tree");
	for (i = 2; i < argc; i += 2) {
		char *a, *b;
		a = argv[i]; b = argv[i+1];
		if (!b || strcmp(a, "-p") || get_sha1_hex(b, parent_sha1[parents]))
			usage("commit-tree <sha1> [-p <sha1>]* < changelog");
		check_valid(parent_sha1[parents], "commit");
		parents++;
	}
	if (!parents)
		fprintf(stderr, "Committing initial tree %s\n", argv[1]);
	pw = getpwuid(getuid());
	if (!pw)
		die("You don't exist. Go away!");
	realgecos = pw->pw_gecos;
	len = strlen(pw->pw_name);
	memcpy(realemail, pw->pw_name, len);
	realemail[len] = '@';
	gethostname(realemail+len+1, sizeof(realemail)-len-1);
	if (!strchr(realemail+len+1, '.')) {
		strcat(realemail, ".");
		getdomainname(realemail+strlen(realemail), sizeof(realemail)-strlen(realemail)-1);
	}
	time(&now);
	tm = localtime(&now);

	strftime(realdate, sizeof(realdate), "%s %z", tm);
	strcpy(date, realdate);

	commitgecos = getenv("COMMIT_AUTHOR_NAME") ? : realgecos;
	commitemail = getenv("COMMIT_AUTHOR_EMAIL") ? : realemail;
	gecos = getenv("AUTHOR_NAME") ? : realgecos;
	email = getenv("AUTHOR_EMAIL") ? : realemail;
	audate = getenv("AUTHOR_DATE");
	if (audate)
		parse_rfc2822_date(audate, date, sizeof(date));

	remove_special(gecos); remove_special(realgecos); remove_special(commitgecos);
	remove_special(email); remove_special(realemail); remove_special(commitemail);

	init_buffer(&buffer, &size);
	add_buffer(&buffer, &size, "tree %s\n", sha1_to_hex(tree_sha1));

	/*
	 * NOTE! This ordering means that the same exact tree merged with a
	 * different order of parents will be a _different_ changeset even
	 * if everything else stays the same.
	 */
	for (i = 0; i < parents; i++)
		add_buffer(&buffer, &size, "parent %s\n", sha1_to_hex(parent_sha1[i]));

	/* Person/date information */
	add_buffer(&buffer, &size, "author %s <%s> %s\n", gecos, email, date);
	add_buffer(&buffer, &size, "committer %s <%s> %s\n\n", commitgecos, commitemail, realdate);

	/* And add the comment */
	while (fgets(comment, sizeof(comment), stdin) != NULL)
		add_buffer(&buffer, &size, "%s", comment);

	finish_buffer("commit ", &buffer, &size);

	write_sha1_file(buffer, size, commit_sha1);
	printf("%s\n", sha1_to_hex(commit_sha1));
	return 0;
}