From a6b062f9873fedceda595670180829e84325440e Mon Sep 17 00:00:00 2001 From: DongHun Kwak Date: Wed, 3 Mar 2021 15:14:45 +0900 Subject: [PATCH] Imported Upstream version 2.1.4 --- Documentation/RelNotes/1.8.5.6.txt | 34 ++++++++++++++++++ Documentation/RelNotes/1.9.5.txt | 34 ++++++++++++++++++ Documentation/RelNotes/2.0.5.txt | 34 ++++++++++++++++++ Documentation/RelNotes/2.1.4.txt | 34 ++++++++++++++++++ Documentation/config.txt | 15 ++++++-- Documentation/git-credential-store.txt | 2 +- Documentation/git.txt | 12 ++++--- Documentation/gitignore.txt | 2 +- GIT-VERSION-GEN | 2 +- RelNotes | 2 +- builtin/clean.c | 2 +- cache.h | 3 ++ config.c | 10 ++++++ config.mak.uname | 3 ++ environment.c | 10 ++++++ fsck.c | 5 ++- path.c | 33 +++++++++++++++++ read-cache.c | 10 ++++-- t/t1014-read-tree-confusing.sh | 62 ++++++++++++++++++++++++++++++++ t/t1450-fsck.sh | 65 ++++++++++++++++++---------------- t/test-lib.sh | 6 +++- unpack-trees.c | 10 +++--- utf8.c | 64 +++++++++++++++++++++++++++++++++ utf8.h | 8 +++++ 24 files changed, 413 insertions(+), 49 deletions(-) create mode 100644 Documentation/RelNotes/1.8.5.6.txt create mode 100644 Documentation/RelNotes/1.9.5.txt create mode 100644 Documentation/RelNotes/2.0.5.txt create mode 100644 Documentation/RelNotes/2.1.4.txt create mode 100755 t/t1014-read-tree-confusing.sh diff --git a/Documentation/RelNotes/1.8.5.6.txt b/Documentation/RelNotes/1.8.5.6.txt new file mode 100644 index 0000000..92ff92b --- /dev/null +++ b/Documentation/RelNotes/1.8.5.6.txt @@ -0,0 +1,34 @@ +Git v1.8.5.6 Release Notes +========================== + +Fixes since v1.8.5.5 +-------------------- + + * We used to allow committing a path ".Git/config" with Git that is + running on a case sensitive filesystem, but an attempt to check out + such a path with Git that runs on a case insensitive filesystem + would have clobbered ".git/config", which is definitely not what + the user would have expected. Git now prevents you from tracking + a path with ".Git" (in any case combination) as a path component. + + * On Windows, certain path components that are different from ".git" + are mapped to ".git", e.g. "git~1/config" is treated as if it were + ".git/config". HFS+ has a similar issue, where certain unicode + codepoints are ignored, e.g. ".g\u200cit/config" is treated as if + it were ".git/config". Pathnames with these potential issues are + rejected on the affected systems. Git on systems that are not + affected by this issue (e.g. Linux) can also be configured to + reject them to ensure cross platform interoperability of the hosted + projects. + + * "git fsck" notices a tree object that records such a path that can + be confused with ".git", and with receive.fsckObjects configuration + set to true, an attempt to "git push" such a tree object will be + rejected. Such a path may not be a problem on a well behaving + filesystem but in order to protect those on HFS+ and on case + insensitive filesystems, this check is enabled on all platforms. + +A big "thanks!" for bringing this issue to us goes to our friends in +the Mercurial land, namely, Matt Mackall and Augie Fackler. + +Also contains typofixes, documentation updates and trivial code clean-ups. diff --git a/Documentation/RelNotes/1.9.5.txt b/Documentation/RelNotes/1.9.5.txt new file mode 100644 index 0000000..8d6ac0c --- /dev/null +++ b/Documentation/RelNotes/1.9.5.txt @@ -0,0 +1,34 @@ +Git v1.9.5 Release Notes +======================== + +Fixes since v1.9.4 +------------------ + + * We used to allow committing a path ".Git/config" with Git that is + running on a case sensitive filesystem, but an attempt to check out + such a path with Git that runs on a case insensitive filesystem + would have clobbered ".git/config", which is definitely not what + the user would have expected. Git now prevents you from tracking + a path with ".Git" (in any case combination) as a path component. + + * On Windows, certain path components that are different from ".git" + are mapped to ".git", e.g. "git~1/config" is treated as if it were + ".git/config". HFS+ has a similar issue, where certain unicode + codepoints are ignored, e.g. ".g\u200cit/config" is treated as if + it were ".git/config". Pathnames with these potential issues are + rejected on the affected systems. Git on systems that are not + affected by this issue (e.g. Linux) can also be configured to + reject them to ensure cross platform interoperability of the hosted + projects. + + * "git fsck" notices a tree object that records such a path that can + be confused with ".git", and with receive.fsckObjects configuration + set to true, an attempt to "git push" such a tree object will be + rejected. Such a path may not be a problem on a well behaving + filesystem but in order to protect those on HFS+ and on case + insensitive filesystems, this check is enabled on all platforms. + +A big "thanks!" for bringing this issue to us goes to our friends in +the Mercurial land, namely, Matt Mackall and Augie Fackler. + +Also contains typofixes, documentation updates and trivial code clean-ups. diff --git a/Documentation/RelNotes/2.0.5.txt b/Documentation/RelNotes/2.0.5.txt new file mode 100644 index 0000000..3a16f69 --- /dev/null +++ b/Documentation/RelNotes/2.0.5.txt @@ -0,0 +1,34 @@ +Git v2.0.5 Release Notes +======================== + +Fixes since v2.0.4 +------------------ + + * We used to allow committing a path ".Git/config" with Git that is + running on a case sensitive filesystem, but an attempt to check out + such a path with Git that runs on a case insensitive filesystem + would have clobbered ".git/config", which is definitely not what + the user would have expected. Git now prevents you from tracking + a path with ".Git" (in any case combination) as a path component. + + * On Windows, certain path components that are different from ".git" + are mapped to ".git", e.g. "git~1/config" is treated as if it were + ".git/config". HFS+ has a similar issue, where certain unicode + codepoints are ignored, e.g. ".g\u200cit/config" is treated as if + it were ".git/config". Pathnames with these potential issues are + rejected on the affected systems. Git on systems that are not + affected by this issue (e.g. Linux) can also be configured to + reject them to ensure cross platform interoperability of the hosted + projects. + + * "git fsck" notices a tree object that records such a path that can + be confused with ".git", and with receive.fsckObjects configuration + set to true, an attempt to "git push" such a tree object will be + rejected. Such a path may not be a problem on a well behaving + filesystem but in order to protect those on HFS+ and on case + insensitive filesystems, this check is enabled on all platforms. + +A big "thanks!" for bringing this issue to us goes to our friends in +the Mercurial land, namely, Matt Mackall and Augie Fackler. + +Also contains typofixes, documentation updates and trivial code clean-ups. diff --git a/Documentation/RelNotes/2.1.4.txt b/Documentation/RelNotes/2.1.4.txt new file mode 100644 index 0000000..d16e5f0 --- /dev/null +++ b/Documentation/RelNotes/2.1.4.txt @@ -0,0 +1,34 @@ +Git v2.1.4 Release Notes +======================== + +Fixes since v2.1.3 +------------------ + + * We used to allow committing a path ".Git/config" with Git that is + running on a case sensitive filesystem, but an attempt to check out + such a path with Git that runs on a case insensitive filesystem + would have clobbered ".git/config", which is definitely not what + the user would have expected. Git now prevents you from tracking + a path with ".Git" (in any case combination) as a path component. + + * On Windows, certain path components that are different from ".git" + are mapped to ".git", e.g. "git~1/config" is treated as if it were + ".git/config". HFS+ has a similar issue, where certain unicode + codepoints are ignored, e.g. ".g\u200cit/config" is treated as if + it were ".git/config". Pathnames with these potential issues are + rejected on the affected systems. Git on systems that are not + affected by this issue (e.g. Linux) can also be configured to + reject them to ensure cross platform interoperability of the hosted + projects. + + * "git fsck" notices a tree object that records such a path that can + be confused with ".git", and with receive.fsckObjects configuration + set to true, an attempt to "git push" such a tree object will be + rejected. Such a path may not be a problem on a well behaving + filesystem but in order to protect those on HFS+ and on case + insensitive filesystems, this check is enabled on all platforms. + +A big "thanks!" for bringing this issue to us goes to our friends in +the Mercurial land, namely, Matt Mackall and Augie Fackler. + +Also contains typofixes, documentation updates and trivial code clean-ups. diff --git a/Documentation/config.txt b/Documentation/config.txt index 382e12c..0a4d22a 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -233,6 +233,17 @@ core.precomposeunicode:: When false, file names are handled fully transparent by Git, which is backward compatible with older versions of Git. +core.protectHFS:: + If set to true, do not allow checkout of paths that would + be considered equivalent to `.git` on an HFS+ filesystem. + Defaults to `true` on Mac OS, and `false` elsewhere. + +core.protectNTFS:: + If set to true, do not allow checkout of paths that would + cause problems with the NTFS filesystem, e.g. conflict with + 8.3 "short" names. + Defaults to `true` on Windows, and `false` elsewhere. + core.trustctime:: If false, the ctime differences between the index and the working tree are ignored; useful when the inode change time @@ -669,7 +680,7 @@ alias.*:: confusion and troubles with script usage, aliases that hide existing Git commands are ignored. Arguments are split by spaces, the usual shell quoting and escaping is supported. - quote pair and a backslash can be used to quote them. + A quote pair or a backslash can be used to quote them. + If the alias expansion is prefixed with an exclamation point, it will be treated as a shell command. For example, defining @@ -2295,7 +2306,7 @@ status.showUntrackedFiles:: files which are not currently tracked by Git. Directories which contain only untracked files, are shown with the directory name only. Showing untracked files means that Git needs to lstat() all - all the files in the whole repository, which might be slow on some + the files in the whole repository, which might be slow on some systems. So, this variable controls how the commands displays the untracked files. Possible values are: + diff --git a/Documentation/git-credential-store.txt b/Documentation/git-credential-store.txt index 8481cae..bc97071 100644 --- a/Documentation/git-credential-store.txt +++ b/Documentation/git-credential-store.txt @@ -29,7 +29,7 @@ linkgit:gitcredentials[7] or `EXAMPLES` below. OPTIONS ------- ---store=:: +--file=:: Use `` to store credentials. The file will have its filesystem permissions set to prevent other users on the system diff --git a/Documentation/git.txt b/Documentation/git.txt index 5627845..78cc101 100644 --- a/Documentation/git.txt +++ b/Documentation/git.txt @@ -43,35 +43,39 @@ unreleased) version of Git, that is available from the 'master' branch of the `git.git` repository. Documentation for older releases are available here: -* link:v2.1.3/git.html[documentation for release 2.1.3] +* link:v2.1.4/git.html[documentation for release 2.1.4] * release notes for + link:RelNotes/2.1.4.txt[2.1.4], link:RelNotes/2.1.3.txt[2.1.3], link:RelNotes/2.1.2.txt[2.1.2], link:RelNotes/2.1.1.txt[2.1.1], link:RelNotes/2.1.0.txt[2.1]. -* link:v2.0.4/git.html[documentation for release 2.0.4] +* link:v2.0.5/git.html[documentation for release 2.0.5] * release notes for + link:RelNotes/2.0.5.txt[2.0.5], link:RelNotes/2.0.4.txt[2.0.4], link:RelNotes/2.0.3.txt[2.0.3], link:RelNotes/2.0.2.txt[2.0.2], link:RelNotes/2.0.1.txt[2.0.1], link:RelNotes/2.0.0.txt[2.0.0]. -* link:v1.9.4/git.html[documentation for release 1.9.4] +* link:v1.9.5/git.html[documentation for release 1.9.5] * release notes for + link:RelNotes/1.9.5.txt[1.9.5], link:RelNotes/1.9.4.txt[1.9.4], link:RelNotes/1.9.3.txt[1.9.3], link:RelNotes/1.9.2.txt[1.9.2], link:RelNotes/1.9.1.txt[1.9.1], link:RelNotes/1.9.0.txt[1.9.0]. -* link:v1.8.5.5/git.html[documentation for release 1.8.5.5] +* link:v1.8.5.6/git.html[documentation for release 1.8.5.6] * release notes for + link:RelNotes/1.8.5.6.txt[1.8.5.6], link:RelNotes/1.8.5.5.txt[1.8.5.5], link:RelNotes/1.8.5.4.txt[1.8.5.4], link:RelNotes/1.8.5.3.txt[1.8.5.3], diff --git a/Documentation/gitignore.txt b/Documentation/gitignore.txt index 8734c15..09e82c3 100644 --- a/Documentation/gitignore.txt +++ b/Documentation/gitignore.txt @@ -77,7 +77,7 @@ PATTERN FORMAT Put a backslash ("`\`") in front of the first hash for patterns that begin with a hash. - - Trailing spaces are ignored unless they are quoted with backlash + - Trailing spaces are ignored unless they are quoted with backslash ("`\`"). - An optional prefix "`!`" which negates the pattern; any diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN index b0500c2..b313654 100755 --- a/GIT-VERSION-GEN +++ b/GIT-VERSION-GEN @@ -1,7 +1,7 @@ #!/bin/sh GVF=GIT-VERSION-FILE -DEF_VER=v2.1.3 +DEF_VER=v2.1.4 LF=' ' diff --git a/RelNotes b/RelNotes index 192f48c..13571a1 120000 --- a/RelNotes +++ b/RelNotes @@ -1 +1 @@ -Documentation/RelNotes/2.1.3.txt \ No newline at end of file +Documentation/RelNotes/2.1.4.txt \ No newline at end of file diff --git a/builtin/clean.c b/builtin/clean.c index 1032563..3beeea6 100644 --- a/builtin/clean.c +++ b/builtin/clean.c @@ -67,7 +67,7 @@ struct menu_item { char hotkey; const char *title; int selected; - int (*fn)(); + int (*fn)(void); }; enum menu_stuff_type { diff --git a/cache.h b/cache.h index dcf3a2a..a258d80 100644 --- a/cache.h +++ b/cache.h @@ -633,6 +633,8 @@ extern int fsync_object_files; extern int core_preload_index; extern int core_apply_sparse_checkout; extern int precomposed_unicode; +extern int protect_hfs; +extern int protect_ntfs; /* * The character that begins a commented line in user-editable file @@ -847,6 +849,7 @@ int normalize_path_copy(char *dst, const char *src); int longest_ancestor_length(const char *path, struct string_list *prefixes); char *strip_path_suffix(const char *path, const char *suffix); int daemon_avoid_alias(const char *path); +extern int is_ntfs_dotgit(const char *name); /* object replacement */ #define LOOKUP_REPLACE_OBJECT 1 diff --git a/config.c b/config.c index 9e42d38..73d8205 100644 --- a/config.c +++ b/config.c @@ -880,6 +880,16 @@ static int git_default_core_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.protecthfs")) { + protect_hfs = git_config_bool(var, value); + return 0; + } + + if (!strcmp(var, "core.protectntfs")) { + protect_ntfs = git_config_bool(var, value); + return 0; + } + /* Add other config variables here and to Documentation/config.txt. */ return 0; } diff --git a/config.mak.uname b/config.mak.uname index 15ee15e..0941e30 100644 --- a/config.mak.uname +++ b/config.mak.uname @@ -100,6 +100,7 @@ ifeq ($(uname_S),Darwin) HAVE_DEV_TTY = YesPlease COMPAT_OBJS += compat/precompose_utf8.o BASIC_CFLAGS += -DPRECOMPOSE_UNICODE + BASIC_CFLAGS += -DPROTECT_HFS_DEFAULT=1 endif ifeq ($(uname_S),SunOS) NEEDS_SOCKET = YesPlease @@ -368,6 +369,7 @@ ifeq ($(uname_S),Windows) EXTLIBS = user32.lib advapi32.lib shell32.lib wininet.lib ws2_32.lib invalidcontinue.obj PTHREAD_LIBS = lib = + BASIC_CFLAGS += -DPROTECT_NTFS_DEFAULT=1 ifndef DEBUG BASIC_CFLAGS += -GL -Os -MD BASIC_LDFLAGS += -LTCG @@ -509,6 +511,7 @@ ifneq (,$(findstring MINGW,$(uname_S))) COMPAT_OBJS += compat/mingw.o compat/winansi.o \ compat/win32/pthread.o compat/win32/syslog.o \ compat/win32/dirent.o + BASIC_CFLAGS += -DPROTECT_NTFS_DEFAULT=1 BASIC_LDFLAGS += -Wl,--large-address-aware EXTLIBS += -lws2_32 GITLIBS += git.res diff --git a/environment.c b/environment.c index 565f652..1ade5c9 100644 --- a/environment.c +++ b/environment.c @@ -64,6 +64,16 @@ int precomposed_unicode = -1; /* see probe_utf8_pathname_composition() */ struct startup_info *startup_info; unsigned long pack_size_limit_cfg; +#ifndef PROTECT_HFS_DEFAULT +#define PROTECT_HFS_DEFAULT 0 +#endif +int protect_hfs = PROTECT_HFS_DEFAULT; + +#ifndef PROTECT_NTFS_DEFAULT +#define PROTECT_NTFS_DEFAULT 0 +#endif +int protect_ntfs = PROTECT_NTFS_DEFAULT; + /* * The character that begins a commented line in user-editable file * that is subject to stripspace. diff --git a/fsck.c b/fsck.c index 56156ff..50c6507 100644 --- a/fsck.c +++ b/fsck.c @@ -6,6 +6,7 @@ #include "commit.h" #include "tag.h" #include "fsck.h" +#include "utf8.h" static int fsck_walk_tree(struct tree *tree, fsck_walk_func walk, void *data) { @@ -170,7 +171,9 @@ static int fsck_tree(struct tree *item, int strict, fsck_error error_func) has_empty_name |= !*name; has_dot |= !strcmp(name, "."); has_dotdot |= !strcmp(name, ".."); - has_dotgit |= !strcmp(name, ".git"); + has_dotgit |= (!strcmp(name, ".git") || + is_hfs_dotgit(name) || + is_ntfs_dotgit(name)); has_zero_pad |= *(char *)desc.buffer == '0'; update_tree_entry(&desc); diff --git a/path.c b/path.c index 3afcdb4..757d0b0 100644 --- a/path.c +++ b/path.c @@ -821,3 +821,36 @@ int daemon_avoid_alias(const char *p) } } } + +static int only_spaces_and_periods(const char *path, size_t len, size_t skip) +{ + if (len < skip) + return 0; + len -= skip; + path += skip; + while (len-- > 0) { + char c = *(path++); + if (c != ' ' && c != '.') + return 0; + } + return 1; +} + +int is_ntfs_dotgit(const char *name) +{ + int len; + + for (len = 0; ; len++) + if (!name[len] || name[len] == '\\' || is_dir_sep(name[len])) { + if (only_spaces_and_periods(name, len, 4) && + !strncasecmp(name, ".git", 4)) + return 1; + if (only_spaces_and_periods(name, len, 5) && + !strncasecmp(name, "git~1", 5)) + return 1; + if (name[len] != '\\') + return 0; + name += len + 1; + len = -1; + } +} diff --git a/read-cache.c b/read-cache.c index 6f0057f..f042693 100644 --- a/read-cache.c +++ b/read-cache.c @@ -16,6 +16,7 @@ #include "varint.h" #include "split-index.h" #include "sigchain.h" +#include "utf8.h" static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, unsigned int options); @@ -775,9 +776,10 @@ static int verify_dotfile(const char *rest) * shares the path end test with the ".." case. */ case 'g': - if (rest[1] != 'i') + case 'G': + if (rest[1] != 'i' && rest[1] != 'I') break; - if (rest[2] != 't') + if (rest[2] != 't' && rest[2] != 'T') break; rest += 2; /* fallthrough */ @@ -801,6 +803,10 @@ int verify_path(const char *path) return 1; if (is_dir_sep(c)) { inside: + if (protect_hfs && is_hfs_dotgit(path)) + return 0; + if (protect_ntfs && is_ntfs_dotgit(path)) + return 0; c = *path++; if ((c == '.' && !verify_dotfile(path)) || is_dir_sep(c) || c == '\0') diff --git a/t/t1014-read-tree-confusing.sh b/t/t1014-read-tree-confusing.sh new file mode 100755 index 0000000..2f5a25d --- /dev/null +++ b/t/t1014-read-tree-confusing.sh @@ -0,0 +1,62 @@ +#!/bin/sh + +test_description='check that read-tree rejects confusing paths' +. ./test-lib.sh + +test_expect_success 'create base tree' ' + echo content >file && + git add file && + git commit -m base && + blob=$(git rev-parse HEAD:file) && + tree=$(git rev-parse HEAD^{tree}) +' + +test_expect_success 'enable core.protectHFS for rejection tests' ' + git config core.protectHFS true +' + +test_expect_success 'enable core.protectNTFS for rejection tests' ' + git config core.protectNTFS true +' + +while read path pretty; do + : ${pretty:=$path} + case "$path" in + *SPACE) + path="${path%SPACE} " + ;; + esac + test_expect_success "reject $pretty at end of path" ' + printf "100644 blob %s\t%s" "$blob" "$path" >tree && + bogus=$(git mktree tree && + bogus=$(git mktree tree && + ok=$(git mktree out && - cat out && - grep "warning.*\\." out - ) -' - -test_expect_success 'fsck notices ".git" in trees' ' - ( - git init dotgit && - cd dotgit && - blob=$(echo foo | git hash-object -w --stdin) && - tab=$(printf "\\t") && - git mktree <<-EOF && - 100644 blob $blob$tab.git - EOF - git fsck 2>out && - cat out && - grep "warning.*\\.git" out - ) -' +while read name path pretty; do + while read mode type; do + : ${pretty:=$path} + test_expect_success "fsck notices $pretty as $type" ' + ( + git init $name-$type && + cd $name-$type && + echo content >file && + git add file && + git commit -m base && + blob=$(git rev-parse :file) && + tree=$(git rev-parse HEAD^{tree}) && + value=$(eval "echo \$$type") && + printf "$mode $type %s\t%s" "$value" "$path" >bad && + bad_tree=$(git mktree out && + cat out && + grep "warning.*tree $bad_tree" out + )' + done <<-\EOF + 100644 blob + 040000 tree + EOF +done <<-EOF +dot . +dotdot .. +dotgit .git +dotgit-case .GIT +dotgit-unicode .gI${u200c}T .gI{u200c}T +dotgit-case2 .Git +git-tilde1 git~1 +dotgitdot .git. +dot-backslash-case .\\\\.GIT\\\\foobar +dotgit-case-backslash .git\\\\foobar +EOF # create a static test repo which is broken by omitting # one particular object ($1, which is looked up via rev-parse diff --git a/t/test-lib.sh b/t/test-lib.sh index b1bc65b..a7a4639 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -169,7 +169,11 @@ _z40=0000000000000000000000000000000000000000 LF=' ' -export _x05 _x40 _z40 LF +# UTF-8 ZERO WIDTH NON-JOINER, which HFS+ ignores +# when case-folding filenames +u200c=$(printf '\342\200\214') + +export _x05 _x40 _z40 LF u200c # Each test should start with something like this, after copyright notices: # diff --git a/unpack-trees.c b/unpack-trees.c index 629c658..256df47 100644 --- a/unpack-trees.c +++ b/unpack-trees.c @@ -98,7 +98,7 @@ void setup_unpack_trees_porcelain(struct unpack_trees_options *opts, opts->unpack_rejects[i].strdup_strings = 1; } -static void do_add_entry(struct unpack_trees_options *o, struct cache_entry *ce, +static int do_add_entry(struct unpack_trees_options *o, struct cache_entry *ce, unsigned int set, unsigned int clear) { clear |= CE_HASHED; @@ -107,8 +107,8 @@ static void do_add_entry(struct unpack_trees_options *o, struct cache_entry *ce, set |= CE_WT_REMOVE; ce->ce_flags = (ce->ce_flags & ~clear) | set; - add_index_entry(&o->result, ce, - ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE); + return add_index_entry(&o->result, ce, + ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE); } static struct cache_entry *dup_entry(const struct cache_entry *ce) @@ -609,7 +609,9 @@ static int unpack_nondirectories(int n, unsigned long mask, for (i = 0; i < n; i++) if (src[i] && src[i] != o->df_conflict_entry) - do_add_entry(o, src[i], 0, 0); + if (do_add_entry(o, src[i], 0, 0)) + return -1; + return 0; } diff --git a/utf8.c b/utf8.c index b30790d..3b77e97 100644 --- a/utf8.c +++ b/utf8.c @@ -565,3 +565,67 @@ int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding) return chrlen; } + +/* + * Pick the next char from the stream, folding as an HFS+ filename comparison + * would. Note that this is _not_ complete by any means. It's just enough + * to make is_hfs_dotgit() work, and should not be used otherwise. + */ +static ucs_char_t next_hfs_char(const char **in) +{ + while (1) { + ucs_char_t out = pick_one_utf8_char(in, NULL); + /* + * check for malformed utf8. Technically this + * gets converted to a percent-sequence, but + * returning 0 is good enough for is_hfs_dotgit + * to realize it cannot be .git + */ + if (!*in) + return 0; + + /* these code points are ignored completely */ + switch (out) { + case 0x200c: /* ZERO WIDTH NON-JOINER */ + case 0x200d: /* ZERO WIDTH JOINER */ + case 0x200e: /* LEFT-TO-RIGHT MARK */ + case 0x200f: /* RIGHT-TO-LEFT MARK */ + case 0x202a: /* LEFT-TO-RIGHT EMBEDDING */ + case 0x202b: /* RIGHT-TO-LEFT EMBEDDING */ + case 0x202c: /* POP DIRECTIONAL FORMATTING */ + case 0x202d: /* LEFT-TO-RIGHT OVERRIDE */ + case 0x202e: /* RIGHT-TO-LEFT OVERRIDE */ + case 0x206a: /* INHIBIT SYMMETRIC SWAPPING */ + case 0x206b: /* ACTIVATE SYMMETRIC SWAPPING */ + case 0x206c: /* INHIBIT ARABIC FORM SHAPING */ + case 0x206d: /* ACTIVATE ARABIC FORM SHAPING */ + case 0x206e: /* NATIONAL DIGIT SHAPES */ + case 0x206f: /* NOMINAL DIGIT SHAPES */ + case 0xfeff: /* ZERO WIDTH NO-BREAK SPACE */ + continue; + } + + /* + * there's a great deal of other case-folding that occurs, + * but this is enough to catch anything that will convert + * to ".git" + */ + return tolower(out); + } +} + +int is_hfs_dotgit(const char *path) +{ + ucs_char_t c; + + if (next_hfs_char(&path) != '.' || + next_hfs_char(&path) != 'g' || + next_hfs_char(&path) != 'i' || + next_hfs_char(&path) != 't') + return 0; + c = next_hfs_char(&path); + if (c && !is_dir_sep(c)) + return 0; + + return 1; +} diff --git a/utf8.h b/utf8.h index 65d0e42..e4d9183 100644 --- a/utf8.h +++ b/utf8.h @@ -42,4 +42,12 @@ static inline char *reencode_string(const char *in, int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding); +/* + * Returns true if the the path would match ".git" after HFS case-folding. + * The path should be NUL-terminated, but we will match variants of both ".git\0" + * and ".git/..." (but _not_ ".../.git"). This makes it suitable for both fsck + * and verify_path(). + */ +int is_hfs_dotgit(const char *path); + #endif -- 2.7.4