mercurial/bdiff.h
author FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
Fri, 03 Mar 2017 02:57:06 +0900
changeset 31210 e1d035905b2e
parent 29541 9631ff5ebbeb
child 34627 72985b390d7c
permissions -rw-r--r--
similar: compare between actual file contents for exact identity Before this patch, similarity detection logic (for addremove and automv) depends entirely on SHA-1 digesting. But this causes incorrect rename detection, if: - removing file A and adding file B occur at same committing, and - SHA-1 hash values of file A and B are same This may prevent security experts from managing sample files for SHAttered issue in Mercurial repository, for example. https://security.googleblog.com/2017/02/announcing-first-sha1-collision.html https://shattered.it/ Hash collision itself isn't so serious for core repository functionality of Mercurial, described by mpm as below, though. https://www.mercurial-scm.org/wiki/mpm/SHA1 This patch compares between actual file contents after hash comparison for exact identity. Even after this patch, SHA-1 is still used, because it is reasonable enough to quickly detect existence of "(almost) same" file. - replacing SHA-1 causes decreasing performance, and - replacement of it has ambiguity, yet Getting content of removed file (= rfctx.data()) at each exact comparison should be cheap enough, even though getting content of added one costs much. ======= ============== ===================== file fctx data() reads from ======= ============== ===================== removed filectx in-memory revlog data added workingfilectx storage ======= ============== =====================

#ifndef _HG_BDIFF_H_
#define _HG_BDIFF_H_

struct bdiff_line {
	int hash, n, e;
	ssize_t len;
	const char *l;
};

struct bdiff_hunk;
struct bdiff_hunk {
	int a1, a2, b1, b2;
	struct bdiff_hunk *next;
};

int bdiff_splitlines(const char *a, ssize_t len, struct bdiff_line **lr);
int bdiff_diff(struct bdiff_line *a, int an, struct bdiff_line *b, int bn,
	struct bdiff_hunk *base);
void bdiff_freehunks(struct bdiff_hunk *l);

#endif