From: Jeff King <peff@peff.net>
To: git@vger.kernel.org
Cc: Eric Sunshine <sunshine@sunshineco.com>,
Junio C Hamano <gitster@pobox.com>,
Johannes Schindelin <Johannes.Schindelin@gmx.de>
Subject: [PATCH 04/10] fast-export: tighten anonymize_mem() interface to handle only strings
Date: Tue, 23 Jun 2020 11:24:54 -0400 [thread overview]
Message-ID: <20200623152454.GD1435482@coredump.intra.peff.net> (raw)
In-Reply-To: <20200623152436.GA50925@coredump.intra.peff.net>
While the anonymize_mem() interface _can_ store arbitrary byte
sequences, none of the callers uses this feature (as of the previous
commit). We'd like to keep it that way, as we'll be exposing the
string-like nature of the anonymization routines to the user. So let's
tighten up the interface a bit:
- don't treat "len" as an out-parameter from anonymize_mem(); this
ensures callers treat the pointer result as a NUL-terminated string
- likewise, don't treat "len" as an out-parameter from generator
functions
- swap out "void *" for "char *" as appropriate to signal that we
don't handle arbitrary memory
- rename the function to anonymize_str()
This will also open up some optimization opportunities in a future
patch.
Note that we can't drop the "len" parameter entirely. Some callers do
pass in partial strings (e.g., "foo/bar", len=3) to avoid copying, and
we need to handle those still.
Signed-off-by: Jeff King <peff@peff.net>
---
builtin/fast-export.c | 53 +++++++++++++++++++++----------------------
1 file changed, 26 insertions(+), 27 deletions(-)
diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index 4a3a4c933e..d8ea067630 100644
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -145,31 +145,30 @@ static int anonymized_entry_cmp(const void *unused_cmp_data,
* the same anonymized string with another. The actual generation
* is farmed out to the generate function.
*/
-static const void *anonymize_mem(struct hashmap *map,
- void *(*generate)(const void *, size_t *),
- const void *orig, size_t *len)
+static const char *anonymize_str(struct hashmap *map,
+ char *(*generate)(const char *, size_t),
+ const char *orig, size_t len)
{
struct anonymized_entry key, *ret;
if (!map->cmpfn)
hashmap_init(map, anonymized_entry_cmp, NULL, 0);
- hashmap_entry_init(&key.hash, memhash(orig, *len));
+ hashmap_entry_init(&key.hash, memhash(orig, len));
key.orig = orig;
- key.orig_len = *len;
+ key.orig_len = len;
ret = hashmap_get_entry(map, &key, hash, NULL);
if (!ret) {
ret = xmalloc(sizeof(*ret));
hashmap_entry_init(&ret->hash, key.hash.hash);
- ret->orig = xmemdupz(orig, *len);
- ret->orig_len = *len;
+ ret->orig = xmemdupz(orig, len);
+ ret->orig_len = len;
ret->anon = generate(orig, len);
- ret->anon_len = *len;
+ ret->anon_len = strlen(ret->anon);
hashmap_put(map, &ret->hash);
}
- *len = ret->anon_len;
return ret->anon;
}
@@ -181,13 +180,13 @@ static const void *anonymize_mem(struct hashmap *map,
*/
static void anonymize_path(struct strbuf *out, const char *path,
struct hashmap *map,
- void *(*generate)(const void *, size_t *))
+ char *(*generate)(const char *, size_t))
{
while (*path) {
const char *end_of_component = strchrnul(path, '/');
size_t len = end_of_component - path;
- const char *c = anonymize_mem(map, generate, path, &len);
- strbuf_add(out, c, len);
+ const char *c = anonymize_str(map, generate, path, len);
+ strbuf_addstr(out, c);
path = end_of_component;
if (*path)
strbuf_addch(out, *path++);
@@ -361,12 +360,12 @@ static void print_path_1(const char *path)
printf("%s", path);
}
-static void *anonymize_path_component(const void *path, size_t *len)
+static char *anonymize_path_component(const char *path, size_t len)
{
static int counter;
struct strbuf out = STRBUF_INIT;
strbuf_addf(&out, "path%d", counter++);
- return strbuf_detach(&out, len);
+ return strbuf_detach(&out, NULL);
}
static void print_path(const char *path)
@@ -383,7 +382,7 @@ static void print_path(const char *path)
}
}
-static void *generate_fake_oid(const void *old, size_t *len)
+static char *generate_fake_oid(const char *old, size_t len)
{
static uint32_t counter = 1; /* avoid null oid */
const unsigned hashsz = the_hash_algo->rawsz;
@@ -399,7 +398,7 @@ static const char *anonymize_oid(const char *oid_hex)
{
static struct hashmap objs;
size_t len = strlen(oid_hex);
- return anonymize_mem(&objs, generate_fake_oid, oid_hex, &len);
+ return anonymize_str(&objs, generate_fake_oid, oid_hex, len);
}
static void show_filemodify(struct diff_queue_struct *q,
@@ -496,12 +495,12 @@ static const char *find_encoding(const char *begin, const char *end)
return bol;
}
-static void *anonymize_ref_component(const void *old, size_t *len)
+static char *anonymize_ref_component(const char *old, size_t len)
{
static int counter;
struct strbuf out = STRBUF_INIT;
strbuf_addf(&out, "ref%d", counter++);
- return strbuf_detach(&out, len);
+ return strbuf_detach(&out, NULL);
}
static const char *anonymize_refname(const char *refname)
@@ -550,13 +549,13 @@ static char *anonymize_commit_message(const char *old)
}
static struct hashmap idents;
-static void *anonymize_ident(const void *old, size_t *len)
+static char *anonymize_ident(const char *old, size_t len)
{
static int counter;
struct strbuf out = STRBUF_INIT;
strbuf_addf(&out, "User %d <user%d@example.com>", counter, counter);
counter++;
- return strbuf_detach(&out, len);
+ return strbuf_detach(&out, NULL);
}
/*
@@ -591,9 +590,9 @@ static void anonymize_ident_line(const char **beg, const char **end)
size_t len;
len = split.mail_end - split.name_begin;
- ident = anonymize_mem(&idents, anonymize_ident,
- split.name_begin, &len);
- strbuf_add(out, ident, len);
+ ident = anonymize_str(&idents, anonymize_ident,
+ split.name_begin, len);
+ strbuf_addstr(out, ident);
strbuf_addch(out, ' ');
strbuf_add(out, split.date_begin, split.tz_end - split.date_begin);
} else {
@@ -733,12 +732,12 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
show_progress();
}
-static void *anonymize_tag(const void *old, size_t *len)
+static char *anonymize_tag(const char *old, size_t len)
{
static int counter;
struct strbuf out = STRBUF_INIT;
strbuf_addf(&out, "tag message %d", counter++);
- return strbuf_detach(&out, len);
+ return strbuf_detach(&out, NULL);
}
static void handle_tail(struct object_array *commits, struct rev_info *revs,
@@ -808,8 +807,8 @@ static void handle_tag(const char *name, struct tag *tag)
name = anonymize_refname(name);
if (message) {
static struct hashmap tags;
- message = anonymize_mem(&tags, anonymize_tag,
- message, &message_size);
+ message = anonymize_str(&tags, anonymize_tag,
+ message, message_size);
}
}
--
2.27.0.517.gbc32778fa3
next prev parent reply other threads:[~2020-06-23 15:24 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-19 13:23 [PATCH 0/3] fast-export: allow dumping anonymization mappings Jeff King
2020-06-19 13:25 ` [PATCH 1/3] fast-export: allow dumping the refname mapping Jeff King
2020-06-19 15:51 ` Eric Sunshine
2020-06-19 16:01 ` Jeff King
2020-06-19 16:18 ` Eric Sunshine
2020-06-19 17:45 ` Jeff King
2020-06-19 18:00 ` Eric Sunshine
2020-06-22 21:30 ` Jeff King
2020-06-19 19:20 ` Junio C Hamano
2020-06-22 21:32 ` Jeff King
2020-06-19 13:26 ` [PATCH 2/3] fast-export: anonymize "master" refname Jeff King
2020-06-19 13:29 ` [PATCH 3/3] fast-export: allow dumping the path mapping Jeff King
2020-06-19 16:00 ` Eric Sunshine
2020-06-19 19:24 ` Junio C Hamano
2020-06-22 21:38 ` Jeff King
2020-06-19 13:51 ` [PATCH 0/3] fast-export: allow dumping anonymization mappings Johannes Schindelin
2020-06-22 16:35 ` Junio C Hamano
2020-06-22 21:47 ` [PATCH v2 0/4] " Jeff King
2020-06-22 21:47 ` [PATCH v2 1/4] fast-export: allow dumping the refname mapping Jeff King
2020-06-22 21:48 ` [PATCH v2 2/4] fast-export: anonymize "master" refname Jeff King
2020-06-22 21:48 ` [PATCH v2 3/4] fast-export: refactor path printing to not rely on stdout Jeff King
2020-06-22 21:48 ` [PATCH v2 4/4] fast-export: allow dumping the path mapping Jeff King
2020-06-23 15:24 ` [alternative 0/10] fast-export: allow seeding the anonymized mapping Jeff King
2020-06-23 15:24 ` [PATCH 01/10] t9351: derive anonymized tree checks from original repo Jeff King
2020-06-23 15:24 ` [PATCH 02/10] fast-export: use xmemdupz() for anonymizing oids Jeff King
2020-06-23 15:24 ` [PATCH 03/10] fast-export: store anonymized oids as hex strings Jeff King
2020-06-24 11:43 ` SZEDER Gábor
2020-06-24 15:54 ` Jeff King
2020-06-25 15:49 ` Jeff King
2020-06-25 20:45 ` SZEDER Gábor
2020-06-25 21:15 ` Jeff King
2020-06-29 13:17 ` Johannes Schindelin
2020-06-30 19:35 ` Jeff King
2020-06-23 15:24 ` Jeff King [this message]
2020-06-23 15:24 ` [PATCH 05/10] fast-export: stop storing lengths in anonymized hashmaps Jeff King
2020-06-23 15:24 ` [PATCH 06/10] fast-export: use a flex array to store anonymized entries Jeff King
2020-06-23 15:25 ` [PATCH 07/10] fast-export: move global "idents" anonymize hashmap into function Jeff King
2020-06-23 15:25 ` [PATCH 08/10] fast-export: add a "data" callback parameter to anonymize_str() Jeff King
2020-06-24 19:58 ` Junio C Hamano
2020-06-23 15:25 ` [PATCH 09/10] fast-export: allow seeding the anonymized mapping Jeff King
2020-06-23 17:16 ` Eric Sunshine
2020-06-23 18:30 ` Jeff King
2020-06-23 20:30 ` Eric Sunshine
2020-06-24 15:47 ` Jeff King
2020-06-23 18:11 ` Eric Sunshine
2020-06-23 18:35 ` Jeff King
2020-06-23 20:35 ` Eric Sunshine
2020-06-24 15:48 ` Jeff King
2020-06-23 15:25 ` [PATCH 10/10] fast-export: anonymize "master" refname Jeff King
2020-06-23 19:34 ` [alternative 0/10] fast-export: allow seeding the anonymized mapping Junio C Hamano
2020-06-23 19:44 ` Jeff King
2020-06-25 19:48 ` [PATCH v2 0/11] " Jeff King
2020-06-25 19:48 ` [PATCH v2 01/11] t9351: derive anonymized tree checks from original repo Jeff King
2020-06-25 19:48 ` [PATCH v2 02/11] fast-export: use xmemdupz() for anonymizing oids Jeff King
2020-06-25 19:48 ` [PATCH v2 03/11] fast-export: store anonymized oids as hex strings Jeff King
2020-06-25 19:48 ` [PATCH v2 04/11] fast-export: tighten anonymize_mem() interface to handle only strings Jeff King
2020-06-25 19:48 ` [PATCH v2 05/11] fast-export: stop storing lengths in anonymized hashmaps Jeff King
2020-06-25 19:48 ` [PATCH v2 06/11] fast-export: use a flex array to store anonymized entries Jeff King
2020-06-25 19:48 ` [PATCH v2 07/11] fast-export: move global "idents" anonymize hashmap into function Jeff King
2020-06-25 19:48 ` [PATCH v2 08/11] fast-export: add a "data" callback parameter to anonymize_str() Jeff King
2020-06-25 19:48 ` [PATCH v2 09/11] fast-export: allow seeding the anonymized mapping Jeff King
2020-06-25 19:48 ` [PATCH v2 10/11] fast-export: anonymize "master" refname Jeff King
2020-06-25 19:48 ` [PATCH v2 11/11] fast-export: use local array to store anonymized oid Jeff King
2020-06-25 21:22 ` [PATCH v2 0/11] fast-export: allow seeding the anonymized mapping Junio C Hamano
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200623152454.GD1435482@coredump.intra.peff.net \
--to=peff@peff.net \
--cc=Johannes.Schindelin@gmx.de \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=sunshine@sunshineco.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).