macOS: ls-files path fails if path of workdir is NFD

Under macOS, `git ls-files path` does not work (gives an error)
if the absolute 'path' contains characters in NFD (decomposed).
This happens when core.precomposeunicode is true, which is the
most common case. The bug report says:

$ cd somewhere          # some safe place, /tmp or ~/tmp etc.
$ mkdir $'u\xcc\x88'    # ü in NFD
$ cd ü                  # or cd $'u\xcc\x88' or cd $'\xc3\xbc'
$ git init
$ git ls-files $'/somewhere/u\xcc\x88'   # NFD
  fatal: /somewhere/ü: '/somewhere/ü' is outside repository at '/somewhere/ü'
$ git ls-files $'/somewhere/\xc3\xbc'    # NFC
(the same error as above)

In the 'fatal:' error message, there are three ü;
the 1st and 2nd are in NFC, the 3rd is in NFD.

Add test cases that follows the bug report, with the simplification
that the 'ü' is replaced by an 'ä', which is already used as NFD and
NFC in t3910.

The solution is to add a call to precompose_string_if_needed()
to this code in setup.c :
`work_tree = precompose_string_if_needed(get_git_work_tree());`

There is, however, a limitation with this very usage of Git:
The (repo) local .gitconfig file is not used, only the global
"core.precomposeunicode" is taken into account, if it is set (or not).
To set it to true is a good recommendation anyway, and here is the
analyzes from Jun T :

The problem is the_repository->config->hash_initialized
is set to 1 before the_repository->commondir is set to ".git".
Due to this, .git/config is never read, and precomposed_unicode
is never set to 1 (remains -1).

run_builtin() {
    setup_git_directory() {
        strbuf_getcwd() {   # setup.c:1542
            precompose_{strbuf,string}_if_needed() {
                # precomposed_unicode is still -1
                git_congig_get_bool("core.precomposeunicode") {
                    git_config_check_init() {
                        repo_read_config() {
                            git_config_init() {
                                # !!!
                                the_repository->config->hash_initialized=1
                                # !!!
                            }
                            # does not read .git/config since
                            # the_repository->commondir is still NULL
                        }
                    }
                }
                returns without converting to NFC
            }
            returns cwd in NFD
        }

        setup_discovered_git_dir() {
            set_git_work_tree(".") {
                repo_set_worktree() {
                    # this function indirectly calls strbuf_getcwd()
                    # --> precompose_{strbuf,string}_if_needed() -->
                    # {git,repo}_config_get_bool("core.precomposeunicode"),
                    # but does not try to read .git/config since
                    # the_repository->config->hash_initialized
                    # is already set to 1 above. And it will not read
                    # .git/config even if hash_initialized is 0
                    # since the_repository->commondir is still NULL.

                    the_repository->worktree = NFD
                }
            }
        }

        setup_git_env() {
            repo_setup_gitdir() {
                repo_set_commondir() {
                    # finally commondir is set here
                    the_repository->commondir = ".git"
                }
            }
        }

    } // END setup_git_directory

Reported-by: Jun T <takimoto-j@kba.biglobe.ne.jp>
Signed-off-by: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/setup.c b/setup.c
index 2e607632dbde807ae76566e282d8f122b1642cda..61f61496ec18a52bf12355f4e7a55852bff6f262 100644 (file)
--- a/setup.c
+++ b/setup.c
@@ -48,7 +48,7 @@ static int abspath_part_inside_repo(char *path)
        size_t wtlen;
        char *path0;
        int off;
-       const char *work_tree = get_git_work_tree();
+       const char *work_tree = precompose_string_if_needed(get_git_work_tree());
        struct strbuf realpath = STRBUF_INIT;
 
        if (!work_tree)

diff --git a/t/t3910-mac-os-precompose.sh b/t/t3910-mac-os-precompose.sh
index 898267a6bd1c8d1320c8e808707ba079c39933fe..6d5918c8feaf9535da63ff801ca28da48d0a18d2 100755 (executable)
--- a/t/t3910-mac-os-precompose.sh
+++ b/t/t3910-mac-os-precompose.sh
@@ -37,6 +37,27 @@ Alongc=$Alongc$Alongc$Alongc$Alongc$Alongc           #50 Byte
 Alongc=$Alongc$Alongc$Alongc$Alongc$Alongc           #250 Byte
 Alongc=$Alongc$AEligatu$AEligatu                     #254 Byte
 
+
+ls_files_nfc_nfd () {
+       test_when_finished "git config --global --unset core.precomposeunicode" &&
+       prglbl=$1
+       prlocl=$2
+       aumlcreat=$3
+       aumllist=$4
+       git config --global core.precomposeunicode $prglbl &&
+       (
+               rm -rf .git &&
+               mkdir -p "somewhere/$prglbl/$prlocl/$aumlcreat" &&
+               mypwd=$PWD &&
+               cd "somewhere/$prglbl/$prlocl/$aumlcreat" &&
+               git init &&
+               git config core.precomposeunicode $prlocl &&
+               git --literal-pathspecs ls-files "$mypwd/somewhere/$prglbl/$prlocl/$aumllist" 2>err &&
+               >expected &&
+               test_cmp expected err
+       )
+}
+
 test_expect_success "detect if nfd needed" '
        precomposeunicode=$(git config core.precomposeunicode) &&
        test "$precomposeunicode" = true &&
@@ -211,8 +232,8 @@ test_expect_success "unicode decomposed: git restore -p . " '
 '
 
 # Test if the global core.precomposeunicode stops autosensing
-# Must be the last test case
 test_expect_success "respect git config --global core.precomposeunicode" '
+       test_when_finished "git config --global --unset core.precomposeunicode" &&
        git config --global core.precomposeunicode true &&
        rm -rf .git &&
        git init &&
@@ -220,4 +241,20 @@ test_expect_success "respect git config --global core.precomposeunicode" '
        test "$precomposeunicode" = "true"
 '
 
+test_expect_success "ls-files false false nfd nfd" '
+       ls_files_nfc_nfd false false $Adiarnfd $Adiarnfd
+'
+
+test_expect_success "ls-files false true nfd nfd" '
+       ls_files_nfc_nfd false true $Adiarnfd $Adiarnfd
+'
+
+test_expect_success "ls-files true false nfd nfd" '
+       ls_files_nfc_nfd true false $Adiarnfd $Adiarnfd
+'
+
+test_expect_success "ls-files true true nfd nfd" '
+       ls_files_nfc_nfd true true $Adiarnfd $Adiarnfd
+'
+
 test_done