##// END OF EJS Templates
templatefuncs: add mailmap template function...
templatefuncs: add mailmap template function This commit adds a template function to support the .mailmap file in Mercurial repositories. The .mailmap file comes from git, and can be used to map new emails and names for old commits. The general use case is that someone may change their name or author commits under different emails and aliases, which would make these commits appear as though they came from different persons. The file allows you to specify the correct name that should be used in place of the author field specified in the commit. The mailmap file has 4 possible formats used to map old "commit" names to new "proper" names: 1. <proper@email.com> <commit@email.com> 2. Proper Name <commit@email.com> 3. Proper Name <proper@email.com> <commit@email.com> 4. Proper Name <proper@email.com> Commit Name <commit@email.com> Essentially there is a commit email present in each mailmap entry, that maps to either an updated name, email, or both. The final possible format allows commits authored by a person who used both an old name and an old email to map to a new name and email. To parse the file, we split by spaces and build a name out of every element that does not start with "<". Once we find an element that does start with "<" we concatenate all the name elements that preceded and add that as a parsed name. We then add the email as the first parsed email. We repeat the process until the end of the line, or a comment is found. We will be left with all parsed names in a list, and all parsed emails in a list, with the 0 index being the proper values and the 1 index being the commit values (if they were specified in the entry). The commit values are added as the keys to a dict, and with the proper fields as the values. The mapname function takes the mapping object and the commit author field and attempts to look for a corresponding entry. To do so we try (commit name, commit email) first, and if no results are returned then (None, commit email) is also looked up. This is due to format 4 from above, where someone may have a mailmap entry with both name and email, and if they don't it is possible they have an entry that uses only the commit email. Differential Revision: https://phab.mercurial-scm.org/D2904

File last commit:

r34802:1f4249c7 default
r37227:2a2ce93e default
Show More
mpatch.c
279 lines | 6.0 KiB | text/x-c | CLexer
/*
mpatch.c - efficient binary patching for Mercurial
This implements a patch algorithm that's O(m + nlog n) where m is the
size of the output and n is the number of patches.
Given a list of binary patches, it unpacks each into a hunk list,
then combines the hunk lists with a treewise recursion to form a
single hunk list. This hunk list is then applied to the original
text.
The text (or binary) fragments are copied directly from their source
Python objects into a preallocated output string to avoid the
allocation of intermediate Python objects. Working memory is about 2x
the total number of hunks.
Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
This software may be used and distributed according to the terms
of the GNU General Public License, incorporated herein by reference.
*/
#include <stdlib.h>
#include <string.h>
#include "bitmanipulation.h"
#include "compat.h"
#include "mpatch.h"
static struct mpatch_flist *lalloc(ssize_t size)
{
struct mpatch_flist *a = NULL;
if (size < 1)
size = 1;
a = (struct mpatch_flist *)malloc(sizeof(struct mpatch_flist));
if (a) {
a->base = (struct mpatch_frag *)malloc(
sizeof(struct mpatch_frag) * size);
if (a->base) {
a->head = a->tail = a->base;
return a;
}
free(a);
}
return NULL;
}
void mpatch_lfree(struct mpatch_flist *a)
{
if (a) {
free(a->base);
free(a);
}
}
static ssize_t lsize(struct mpatch_flist *a)
{
return a->tail - a->head;
}
/* move hunks in source that are less cut to dest, compensating
for changes in offset. the last hunk may be split if necessary.
*/
static int gather(struct mpatch_flist *dest, struct mpatch_flist *src, int cut,
int offset)
{
struct mpatch_frag *d = dest->tail, *s = src->head;
int postend, c, l;
while (s != src->tail) {
if (s->start + offset >= cut)
break; /* we've gone far enough */
postend = offset + s->start + s->len;
if (postend <= cut) {
/* save this hunk */
offset += s->start + s->len - s->end;
*d++ = *s++;
} else {
/* break up this hunk */
c = cut - offset;
if (s->end < c)
c = s->end;
l = cut - offset - s->start;
if (s->len < l)
l = s->len;
offset += s->start + l - c;
d->start = s->start;
d->end = c;
d->len = l;
d->data = s->data;
d++;
s->start = c;
s->len = s->len - l;
s->data = s->data + l;
break;
}
}
dest->tail = d;
src->head = s;
return offset;
}
/* like gather, but with no output list */
static int discard(struct mpatch_flist *src, int cut, int offset)
{
struct mpatch_frag *s = src->head;
int postend, c, l;
while (s != src->tail) {
if (s->start + offset >= cut)
break;
postend = offset + s->start + s->len;
if (postend <= cut) {
offset += s->start + s->len - s->end;
s++;
} else {
c = cut - offset;
if (s->end < c)
c = s->end;
l = cut - offset - s->start;
if (s->len < l)
l = s->len;
offset += s->start + l - c;
s->start = c;
s->len = s->len - l;
s->data = s->data + l;
break;
}
}
src->head = s;
return offset;
}
/* combine hunk lists a and b, while adjusting b for offset changes in a/
this deletes a and b and returns the resultant list. */
static struct mpatch_flist *combine(struct mpatch_flist *a,
struct mpatch_flist *b)
{
struct mpatch_flist *c = NULL;
struct mpatch_frag *bh, *ct;
int offset = 0, post;
if (a && b)
c = lalloc((lsize(a) + lsize(b)) * 2);
if (c) {
for (bh = b->head; bh != b->tail; bh++) {
/* save old hunks */
offset = gather(c, a, bh->start, offset);
/* discard replaced hunks */
post = discard(a, bh->end, offset);
/* insert new hunk */
ct = c->tail;
ct->start = bh->start - offset;
ct->end = bh->end - post;
ct->len = bh->len;
ct->data = bh->data;
c->tail++;
offset = post;
}
/* hold on to tail from a */
memcpy(c->tail, a->head, sizeof(struct mpatch_frag) * lsize(a));
c->tail += lsize(a);
}
mpatch_lfree(a);
mpatch_lfree(b);
return c;
}
/* decode a binary patch into a hunk list */
int mpatch_decode(const char *bin, ssize_t len, struct mpatch_flist **res)
{
struct mpatch_flist *l;
struct mpatch_frag *lt;
int pos = 0;
/* assume worst case size, we won't have many of these lists */
l = lalloc(len / 12 + 1);
if (!l)
return MPATCH_ERR_NO_MEM;
lt = l->tail;
while (pos >= 0 && pos < len) {
lt->start = getbe32(bin + pos);
lt->end = getbe32(bin + pos + 4);
lt->len = getbe32(bin + pos + 8);
lt->data = bin + pos + 12;
pos += 12 + lt->len;
if (lt->start > lt->end || lt->len < 0)
break; /* sanity check */
lt++;
}
if (pos != len) {
mpatch_lfree(l);
return MPATCH_ERR_CANNOT_BE_DECODED;
}
l->tail = lt;
*res = l;
return 0;
}
/* calculate the size of resultant text */
ssize_t mpatch_calcsize(ssize_t len, struct mpatch_flist *l)
{
ssize_t outlen = 0, last = 0;
struct mpatch_frag *f = l->head;
while (f != l->tail) {
if (f->start < last || f->end > len) {
return MPATCH_ERR_INVALID_PATCH;
}
outlen += f->start - last;
last = f->end;
outlen += f->len;
f++;
}
outlen += len - last;
return outlen;
}
int mpatch_apply(char *buf, const char *orig, ssize_t len,
struct mpatch_flist *l)
{
struct mpatch_frag *f = l->head;
int last = 0;
char *p = buf;
while (f != l->tail) {
if (f->start < last || f->end > len) {
return MPATCH_ERR_INVALID_PATCH;
}
memcpy(p, orig + last, f->start - last);
p += f->start - last;
memcpy(p, f->data, f->len);
last = f->end;
p += f->len;
f++;
}
memcpy(p, orig + last, len - last);
return 0;
}
/* recursively generate a patch of all bins between start and end */
struct mpatch_flist *
mpatch_fold(void *bins, struct mpatch_flist *(*get_next_item)(void *, ssize_t),
ssize_t start, ssize_t end)
{
ssize_t len;
if (start + 1 == end) {
/* trivial case, output a decoded list */
return get_next_item(bins, start);
}
/* divide and conquer, memory management is elsewhere */
len = (end - start) / 2;
return combine(mpatch_fold(bins, get_next_item, start, start + len),
mpatch_fold(bins, get_next_item, start + len, end));
}