Merge branch 'cn/bom-in-gitignore' into maint

Teach the codepaths that read .gitignore and .gitattributes files
that these files encoded in UTF-8 may have UTF-8 BOM marker at the
beginning; this makes it in line with what we do for configuration
files already.

* cn/bom-in-gitignore:
attr: skip UTF8 BOM at the beginning of the input file
config: use utf8_bom[] from utf.[ch] in git_parse_source()
utf8-bom: introduce skip_utf8_bom() helper
add_excludes_from_file: clarify the bom skipping logic
dir: allow a BOM at the beginning of exclude files

diff --git a/attr.c b/attr.c
index 1f9eebd2ddb7fe8a561500c41f33a52d1fb4fdd1..7f445965c1886fe8cb53966969b48f4b0bde4826 100644 (file)
--- a/attr.c
+++ b/attr.c
@@ -12,6 +12,7 @@
 #include "exec_cmd.h"
 #include "attr.h"
 #include "dir.h"
+#include "utf8.h"
 
 const char git_attr__true[] = "(builtin)true";
 const char git_attr__false[] = "\0(builtin)false";
@@ -379,8 +380,12 @@ static struct attr_stack *read_attr_from_file(const char *path, int macro_ok)
                return NULL;
        }
        res = xcalloc(1, sizeof(*res));
-       while (fgets(buf, sizeof(buf), fp))
-               handle_attr_line(res, buf, path, ++lineno, macro_ok);
+       while (fgets(buf, sizeof(buf), fp)) {
+               char *bufp = buf;
+               if (!lineno)
+                       skip_utf8_bom(&bufp, strlen(bufp));
+               handle_attr_line(res, bufp, path, ++lineno, macro_ok);
+       }
        fclose(fp);
        return res;
 }

diff --git a/config.c b/config.c
index 66c0a51bce529e4c027f11017697a62dd737b3bd..c4424c01388496b5995e19f9601f0c87b9fdd3c0 100644 (file)
--- a/config.c
+++ b/config.c
@@ -12,6 +12,7 @@
 #include "quote.h"
 #include "hashmap.h"
 #include "string-list.h"
+#include "utf8.h"
 
 struct config_source {
        struct config_source *prev;
@@ -417,8 +418,7 @@ static int git_parse_source(config_fn_t fn, void *data)
        struct strbuf *var = &cf->var;
 
        /* U+FEFF Byte Order Mark in UTF8 */
-       static const unsigned char *utf8_bom = (unsigned char *) "\xef\xbb\xbf";
-       const unsigned char *bomptr = utf8_bom;
+       const char *bomptr = utf8_bom;
 
        for (;;) {
                int c = get_next_char();
@@ -426,7 +426,7 @@ static int git_parse_source(config_fn_t fn, void *data)
                        /* We are at the file beginning; skip UTF8-encoded BOM
                         * if present. Sane editors won't put this in on their
                         * own, but e.g. Windows Notepad will do it happily. */
-                       if ((unsigned char) c == *bomptr) {
+                       if (c == (*bomptr & 0377)) {
                                bomptr++;
                                continue;
                        } else {

diff --git a/dir.c b/dir.c
index 0943a81964ddb7b5b1d83c9c8eafe2b3b2b9da09..a3e70734004e5da22dce9ba4062c0d6684061855 100644 (file)
--- a/dir.c
+++ b/dir.c
@@ -12,6 +12,7 @@
 #include "refs.h"
 #include "wildmatch.h"
 #include "pathspec.h"
+#include "utf8.h"
 
 struct path_simplify {
        int len;
@@ -617,7 +618,12 @@ int add_excludes_from_file_to_list(const char *fname,
        }
 
        el->filebuf = buf;
+
+       if (skip_utf8_bom(&buf, size))
+               size -= buf - el->filebuf;
+
        entry = buf;
+
        for (i = 0; i < size; i++) {
                if (buf[i] == '\n') {
                        if (entry != buf + i && entry[0] != '#') {

diff --git a/t/t7061-wtstatus-ignore.sh b/t/t7061-wtstatus-ignore.sh
index 460789b4d85241eb51c0c1a5a1f4be7d4a0d7154..cdc0747bf01b0598a2e864073887896162815019 100755 (executable)
--- a/t/t7061-wtstatus-ignore.sh
+++ b/t/t7061-wtstatus-ignore.sh
@@ -20,6 +20,15 @@ test_expect_success 'status untracked directory with --ignored' '
        test_cmp expected actual
 '
 
+test_expect_success 'same with gitignore starting with BOM' '
+       printf "\357\273\277ignored\n" >.gitignore &&
+       mkdir -p untracked &&
+       : >untracked/ignored &&
+       : >untracked/uncommitted &&
+       git status --porcelain --ignored >actual &&
+       test_cmp expected actual
+'
+
 cat >expected <<\EOF
 ?? .gitignore
 ?? actual

diff --git a/utf8.c b/utf8.c
index 520fbb4994ab1bdcfa0bc4589a0ca5131a89c490..28e6d76a425db4c16a8cc32e6f17c7aa72c2b1f0 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -633,3 +633,14 @@ int is_hfs_dotgit(const char *path)
 
        return 1;
 }
+
+const char utf8_bom[] = "\357\273\277";
+
+int skip_utf8_bom(char **text, size_t len)
+{
+       if (len < strlen(utf8_bom) ||
+           memcmp(*text, utf8_bom, strlen(utf8_bom)))
+               return 0;
+       *text += strlen(utf8_bom);
+       return 1;
+}

diff --git a/utf8.h b/utf8.h
index e4d9183c5fec81f8dbc75d1f2aea136f9b397a72..e7b2aa416844a0b2ccb2d2cf8a1bce68c4d60be1 100644 (file)
--- a/utf8.h
+++ b/utf8.h
@@ -13,6 +13,9 @@ int same_encoding(const char *, const char *);
 __attribute__((format (printf, 2, 3)))
 int utf8_fprintf(FILE *, const char *, ...);
 
+extern const char utf8_bom[];
+extern int skip_utf8_bom(char **, size_t);
+
 void strbuf_add_wrapped_text(struct strbuf *buf,
                const char *text, int indent, int indent2, int width);
 void strbuf_add_wrapped_bytes(struct strbuf *buf, const char *data, int len,