From: "Ezekiel Newren via GitGitGadget" <gitgitgadget@gmail•com>
To: git@vger•kernel.org
Cc: Kristoffer Haugsbakk <kristofferhaugsbakk@fastmail•com>,
Patrick Steinhardt <ps@pks•im>,
Phillip Wood <phillip.wood123@gmail•com>,
Chris Torek <chris.torek@gmail•com>,
Ezekiel Newren <ezekielnewren@gmail•com>,
Ezekiel Newren <ezekielnewren@gmail•com>
Subject: [PATCH v4 05/10] xdiff: use unambiguous types in xdl_hash_record()
Date: Fri, 14 Nov 2025 22:36:51 +0000 [thread overview]
Message-ID: <2ee9a74653e77c395659c8540d9139179478e3fd.1763159816.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.2070.v4.git.git.1763159816.gitgitgadget@gmail.com>
From: Ezekiel Newren <ezekielnewren@gmail•com>
Convert the function signature and body to use unambiguous types. char
is changed to uint8_t because this function processes bytes in memory.
unsigned long to uint64_t so that the hash output is consistent across
platforms. `flags` was changed from long to uint64_t to ensure the
high order bits are not dropped on platforms that treat long as 32
bits.
Signed-off-by: Ezekiel Newren <ezekielnewren@gmail•com>
---
xdiff-interface.c | 2 +-
xdiff/xprepare.c | 6 +++---
xdiff/xutils.c | 28 ++++++++++++++--------------
xdiff/xutils.h | 6 +++---
4 files changed, 21 insertions(+), 21 deletions(-)
diff --git a/xdiff-interface.c b/xdiff-interface.c
index 4971f722b3..1a35556380 100644
--- a/xdiff-interface.c
+++ b/xdiff-interface.c
@@ -300,7 +300,7 @@ void xdiff_clear_find_func(xdemitconf_t *xecfg)
unsigned long xdiff_hash_string(const char *s, size_t len, long flags)
{
- return xdl_hash_record(&s, s + len, flags);
+ return xdl_hash_record((uint8_t const**)&s, (uint8_t const*)s + len, flags);
}
int xdiff_compare_lines(const char *l1, long s1,
diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
index b3219aed3e..85e56021da 100644
--- a/xdiff/xprepare.c
+++ b/xdiff/xprepare.c
@@ -137,8 +137,8 @@ static void xdl_free_ctx(xdfile_t *xdf)
static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp,
xdlclassifier_t *cf, xdfile_t *xdf) {
long bsize;
- unsigned long hav;
- char const *blk, *cur, *top, *prev;
+ uint64_t hav;
+ uint8_t const *blk, *cur, *top, *prev;
xrecord_t *crec;
xdf->rindex = NULL;
@@ -156,7 +156,7 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
if (XDL_ALLOC_GROW(xdf->recs, xdf->nrec + 1, narec))
goto abort;
crec = &xdf->recs[xdf->nrec++];
- crec->ptr = (uint8_t const *)prev;
+ crec->ptr = prev;
crec->size = cur - prev;
crec->ha = hav;
if (xdl_classify_record(pass, cf, crec) < 0)
diff --git a/xdiff/xutils.c b/xdiff/xutils.c
index 7be063bfb6..77ee1ad9c8 100644
--- a/xdiff/xutils.c
+++ b/xdiff/xutils.c
@@ -249,11 +249,11 @@ int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags)
return 1;
}
-unsigned long xdl_hash_record_with_whitespace(char const **data,
- char const *top, long flags) {
- unsigned long ha = 5381;
- char const *ptr = *data;
- int cr_at_eol_only = (flags & XDF_WHITESPACE_FLAGS) == XDF_IGNORE_CR_AT_EOL;
+uint64_t xdl_hash_record_with_whitespace(uint8_t const **data,
+ uint8_t const *top, uint64_t flags) {
+ uint64_t ha = 5381;
+ uint8_t const *ptr = *data;
+ bool cr_at_eol_only = (flags & XDF_WHITESPACE_FLAGS) == XDF_IGNORE_CR_AT_EOL;
for (; ptr < top && *ptr != '\n'; ptr++) {
if (cr_at_eol_only) {
@@ -263,8 +263,8 @@ unsigned long xdl_hash_record_with_whitespace(char const **data,
continue;
}
else if (XDL_ISSPACE(*ptr)) {
- const char *ptr2 = ptr;
- int at_eol;
+ const uint8_t *ptr2 = ptr;
+ bool at_eol;
while (ptr + 1 < top && XDL_ISSPACE(ptr[1])
&& ptr[1] != '\n')
ptr++;
@@ -274,20 +274,20 @@ unsigned long xdl_hash_record_with_whitespace(char const **data,
else if (flags & XDF_IGNORE_WHITESPACE_CHANGE
&& !at_eol) {
ha += (ha << 5);
- ha ^= (unsigned long) ' ';
+ ha ^= (uint64_t) ' ';
}
else if (flags & XDF_IGNORE_WHITESPACE_AT_EOL
&& !at_eol) {
while (ptr2 != ptr + 1) {
ha += (ha << 5);
- ha ^= (unsigned long) *ptr2;
+ ha ^= (uint64_t) *ptr2;
ptr2++;
}
}
continue;
}
ha += (ha << 5);
- ha ^= (unsigned long) *ptr;
+ ha ^= (uint64_t) *ptr;
}
*data = ptr < top ? ptr + 1: ptr;
@@ -304,9 +304,9 @@ unsigned long xdl_hash_record_with_whitespace(char const **data,
#define REASSOC_FENCE(x, y)
#endif
-unsigned long xdl_hash_record_verbatim(char const **data, char const *top) {
- unsigned long ha = 5381, c0, c1;
- char const *ptr = *data;
+uint64_t xdl_hash_record_verbatim(uint8_t const **data, uint8_t const *top) {
+ uint64_t ha = 5381, c0, c1;
+ uint8_t const *ptr = *data;
#if 0
/*
* The baseline form of the optimized loop below. This is the djb2
@@ -314,7 +314,7 @@ unsigned long xdl_hash_record_verbatim(char const **data, char const *top) {
*/
for (; ptr < top && *ptr != '\n'; ptr++) {
ha += (ha << 5);
- ha += (unsigned long) *ptr;
+ ha += (uint64_t) *ptr;
}
*data = ptr < top ? ptr + 1: ptr;
#else
diff --git a/xdiff/xutils.h b/xdiff/xutils.h
index 13f6831047..615b4a9d35 100644
--- a/xdiff/xutils.h
+++ b/xdiff/xutils.h
@@ -34,9 +34,9 @@ void *xdl_cha_alloc(chastore_t *cha);
long xdl_guess_lines(mmfile_t *mf, long sample);
int xdl_blankline(const char *line, long size, long flags);
int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags);
-unsigned long xdl_hash_record_verbatim(char const **data, char const *top);
-unsigned long xdl_hash_record_with_whitespace(char const **data, char const *top, long flags);
-static inline unsigned long xdl_hash_record(char const **data, char const *top, long flags)
+uint64_t xdl_hash_record_verbatim(uint8_t const **data, uint8_t const *top);
+uint64_t xdl_hash_record_with_whitespace(uint8_t const **data, uint8_t const *top, uint64_t flags);
+static inline uint64_t xdl_hash_record(uint8_t const **data, uint8_t const *top, uint64_t flags)
{
if (flags & XDF_WHITESPACE_FLAGS)
return xdl_hash_record_with_whitespace(data, top, flags);
--
gitgitgadget
next prev parent reply other threads:[~2025-11-14 22:37 UTC|newest]
Thread overview: 118+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-15 21:18 [PATCH 0/9] Xdiff cleanup part2 Ezekiel Newren via GitGitGadget
2025-10-15 21:18 ` [PATCH 1/9] xdiff: use ssize_t for dstart/dend, make them last in xdfile_t Ezekiel Newren via GitGitGadget
2025-10-21 11:32 ` Phillip Wood
2025-10-21 17:18 ` Junio C Hamano
2025-10-22 21:07 ` Ezekiel Newren
2025-10-22 21:38 ` Junio C Hamano
2025-10-22 21:51 ` Ezekiel Newren
2025-10-15 21:18 ` [PATCH 2/9] xdiff: make xrecord_t.ptr a uint8_t instead of char Ezekiel Newren via GitGitGadget
2025-10-16 21:51 ` Kristoffer Haugsbakk
2025-10-21 8:33 ` Patrick Steinhardt
2025-10-22 21:12 ` Ezekiel Newren
2025-10-21 13:13 ` Phillip Wood
2025-10-21 18:15 ` Junio C Hamano
2025-10-22 13:27 ` Phillip Wood
2025-10-22 20:55 ` Ezekiel Newren
2025-10-15 21:18 ` [PATCH 3/9] xdiff: use size_t for xrecord_t.size Ezekiel Newren via GitGitGadget
2025-10-15 21:18 ` [PATCH 4/9] xdiff: use unambiguous types in xdl_hash_record() Ezekiel Newren via GitGitGadget
2025-10-21 8:33 ` Patrick Steinhardt
2025-10-22 21:20 ` Ezekiel Newren
2025-10-23 5:49 ` Patrick Steinhardt
2025-10-15 21:18 ` [PATCH 5/9] xdiff: split xrecord_t.ha into line_hash and minimal_perfect_hash Ezekiel Newren via GitGitGadget
2025-10-20 23:29 ` Ezekiel Newren
2025-10-21 5:10 ` Junio C Hamano
2025-10-21 8:33 ` Patrick Steinhardt
2025-10-21 10:03 ` Phillip Wood
2025-10-21 11:16 ` Chris Torek
2025-10-22 21:31 ` Ezekiel Newren
2025-10-15 21:18 ` [PATCH 6/9] xdiff: make xdfile_t.nrec a size_t instead of long Ezekiel Newren via GitGitGadget
2025-10-15 21:18 ` [PATCH 7/9] xdiff: make xdfile_t.nreff " Ezekiel Newren via GitGitGadget
2025-10-15 21:18 ` [PATCH 8/9] xdiff: change rindex from long to size_t in xdfile_t Ezekiel Newren via GitGitGadget
2025-10-21 8:34 ` Patrick Steinhardt
2025-10-22 22:14 ` Ezekiel Newren
2025-10-23 5:49 ` Patrick Steinhardt
2025-10-15 21:18 ` [PATCH 9/9] xdiff: rename rindex -> reference_index Ezekiel Newren via GitGitGadget
2025-10-15 21:28 ` [PATCH 0/9] Xdiff cleanup part2 Junio C Hamano
2025-10-21 13:28 ` Phillip Wood
2025-10-21 13:41 ` Junio C Hamano
2025-10-29 22:19 ` [PATCH v2 00/10] " Ezekiel Newren via GitGitGadget
2025-10-29 22:19 ` [PATCH v2 01/10] doc: define unambiguous type mappings across C and Rust Ezekiel Newren via GitGitGadget
2025-11-06 9:55 ` Phillip Wood
2025-11-06 22:52 ` Ezekiel Newren
2025-11-09 14:14 ` Phillip Wood
2025-10-29 22:19 ` [PATCH v2 02/10] xdiff: use ssize_t for dstart/dend, make them last in xdfile_t Ezekiel Newren via GitGitGadget
2025-11-06 9:55 ` Phillip Wood
2025-11-06 22:56 ` Ezekiel Newren
2025-10-29 22:19 ` [PATCH v2 03/10] xdiff: make xrecord_t.ptr a uint8_t instead of char Ezekiel Newren via GitGitGadget
2025-11-06 10:49 ` Phillip Wood
2025-11-06 23:13 ` Ezekiel Newren
2025-11-06 10:55 ` Phillip Wood
2025-11-06 23:14 ` Ezekiel Newren
2025-10-29 22:19 ` [PATCH v2 04/10] xdiff: use size_t for xrecord_t.size Ezekiel Newren via GitGitGadget
2025-10-29 22:19 ` [PATCH v2 05/10] xdiff: use unambiguous types in xdl_hash_record() Ezekiel Newren via GitGitGadget
2025-10-29 22:19 ` [PATCH v2 06/10] xdiff: split xrecord_t.ha into line_hash and minimal_perfect_hash Ezekiel Newren via GitGitGadget
2025-11-06 11:00 ` Phillip Wood
2025-11-06 23:20 ` Ezekiel Newren
2025-10-29 22:19 ` [PATCH v2 07/10] xdiff: make xdfile_t.nrec a size_t instead of long Ezekiel Newren via GitGitGadget
2025-10-29 22:19 ` [PATCH v2 08/10] xdiff: make xdfile_t.nreff " Ezekiel Newren via GitGitGadget
2025-10-29 22:19 ` [PATCH v2 09/10] xdiff: change rindex from long to size_t in xdfile_t Ezekiel Newren via GitGitGadget
2025-10-29 22:19 ` [PATCH v2 10/10] xdiff: rename rindex -> reference_index Ezekiel Newren via GitGitGadget
2025-10-30 14:26 ` [PATCH v2 00/10] Xdiff cleanup part2 Junio C Hamano
2025-11-11 19:42 ` [PATCH v3 " Ezekiel Newren via GitGitGadget
2025-11-11 19:42 ` [PATCH v3 01/10] doc: define unambiguous type mappings across C and Rust Ezekiel Newren via GitGitGadget
2025-11-11 20:52 ` Junio C Hamano
2025-11-11 21:05 ` Junio C Hamano
2025-11-11 19:42 ` [PATCH v3 02/10] xdiff: use ptrdiff_t for dstart/dend Ezekiel Newren via GitGitGadget
2025-11-11 22:23 ` Junio C Hamano
2025-11-11 19:42 ` [PATCH v3 03/10] xdiff: make xrecord_t.ptr a uint8_t instead of char Ezekiel Newren via GitGitGadget
2025-11-11 22:53 ` Junio C Hamano
2025-11-11 19:42 ` [PATCH v3 04/10] xdiff: use size_t for xrecord_t.size Ezekiel Newren via GitGitGadget
2025-11-11 23:08 ` Junio C Hamano
2025-11-14 6:02 ` Ezekiel Newren
2025-11-14 16:31 ` Junio C Hamano
2025-11-11 19:42 ` [PATCH v3 05/10] xdiff: use unambiguous types in xdl_hash_record() Ezekiel Newren via GitGitGadget
2025-11-11 19:42 ` [PATCH v3 06/10] xdiff: split xrecord_t.ha into line_hash and minimal_perfect_hash Ezekiel Newren via GitGitGadget
2025-11-11 23:21 ` Junio C Hamano
2025-11-14 5:41 ` Ezekiel Newren
2025-11-14 20:06 ` Junio C Hamano
2025-11-11 19:42 ` [PATCH v3 07/10] xdiff: make xdfile_t.nrec a size_t instead of long Ezekiel Newren via GitGitGadget
2025-11-11 19:42 ` [PATCH v3 08/10] xdiff: make xdfile_t.nreff " Ezekiel Newren via GitGitGadget
2025-11-11 19:42 ` [PATCH v3 09/10] xdiff: change rindex from long to size_t in xdfile_t Ezekiel Newren via GitGitGadget
2025-11-11 19:42 ` [PATCH v3 10/10] xdiff: rename rindex -> reference_index Ezekiel Newren via GitGitGadget
2025-11-11 23:40 ` [PATCH v3 00/10] Xdiff cleanup part2 Junio C Hamano
2025-11-14 5:52 ` Ezekiel Newren
2025-11-14 22:36 ` [PATCH v4 " Ezekiel Newren via GitGitGadget
2025-11-14 22:36 ` [PATCH v4 01/10] doc: define unambiguous type mappings across C and Rust Ezekiel Newren via GitGitGadget
2025-11-15 3:06 ` Ramsay Jones
2025-11-15 3:41 ` Ben Knoble
2025-11-15 14:55 ` Ramsay Jones
2025-11-15 16:42 ` Junio C Hamano
2025-11-15 16:59 ` D. Ben Knoble
2025-11-15 20:03 ` Junio C Hamano
2025-11-17 1:20 ` Junio C Hamano
2025-11-17 2:08 ` Ramsay Jones
2025-11-14 22:36 ` [PATCH v4 02/10] xdiff: use ptrdiff_t for dstart/dend Ezekiel Newren via GitGitGadget
2025-11-14 22:36 ` [PATCH v4 03/10] xdiff: make xrecord_t.ptr a uint8_t instead of char Ezekiel Newren via GitGitGadget
2025-11-15 8:26 ` Junio C Hamano
2025-11-18 20:55 ` Ezekiel Newren
2025-11-14 22:36 ` [PATCH v4 04/10] xdiff: use size_t for xrecord_t.size Ezekiel Newren via GitGitGadget
2025-11-14 22:36 ` Ezekiel Newren via GitGitGadget [this message]
2025-11-14 22:36 ` [PATCH v4 06/10] xdiff: split xrecord_t.ha into line_hash and minimal_perfect_hash Ezekiel Newren via GitGitGadget
2025-11-14 22:36 ` [PATCH v4 07/10] xdiff: make xdfile_t.nrec a size_t instead of long Ezekiel Newren via GitGitGadget
2025-11-14 22:36 ` [PATCH v4 08/10] xdiff: make xdfile_t.nreff " Ezekiel Newren via GitGitGadget
2025-11-14 22:36 ` [PATCH v4 09/10] xdiff: change rindex from long to size_t in xdfile_t Ezekiel Newren via GitGitGadget
2025-11-14 22:36 ` [PATCH v4 10/10] xdiff: rename rindex -> reference_index Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 00/10] Xdiff cleanup part2 Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 01/10] doc: define unambiguous type mappings across C and Rust Ezekiel Newren via GitGitGadget
2025-11-18 23:46 ` Ramsay Jones
2025-11-19 4:14 ` Junio C Hamano
2025-11-18 22:34 ` [PATCH v5 02/10] xdiff: use ptrdiff_t for dstart/dend Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 03/10] xdiff: make xrecord_t.ptr a uint8_t instead of char Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 04/10] xdiff: use size_t for xrecord_t.size Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 05/10] xdiff: use unambiguous types in xdl_hash_record() Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 06/10] xdiff: split xrecord_t.ha into line_hash and minimal_perfect_hash Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 07/10] xdiff: make xdfile_t.nrec a size_t instead of long Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 08/10] xdiff: make xdfile_t.nreff " Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 09/10] xdiff: change rindex from long to size_t in xdfile_t Ezekiel Newren via GitGitGadget
2025-11-18 22:34 ` [PATCH v5 10/10] xdiff: rename rindex -> reference_index Ezekiel Newren via GitGitGadget
2025-11-18 23:11 ` [PATCH v5 00/10] Xdiff cleanup part2 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
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=2ee9a74653e77c395659c8540d9139179478e3fd.1763159816.git.gitgitgadget@gmail.com \
--to=gitgitgadget@gmail$(echo .)com \
--cc=chris.torek@gmail$(echo .)com \
--cc=ezekielnewren@gmail$(echo .)com \
--cc=git@vger$(echo .)kernel.org \
--cc=kristofferhaugsbakk@fastmail$(echo .)com \
--cc=phillip.wood123@gmail$(echo .)com \
--cc=ps@pks$(echo .)im \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox