Add 'ident' conversion.

The 'ident' attribute set to path squashes "$ident:<any bytes
except dollor sign>$" to "$ident$" upon checkin, and expands it
to "$ident: <blob SHA-1> $" upon checkout.

As we have two conversions that affect checkin/checkout paths,
clarify how they interact with each other.

Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index 857d55a409b80f0beaa8b98e1e04f922798241e3..b6f90f6f37b5ab28096fdc3a7cb3dbc35fa82175 100644 (file)
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -78,12 +78,17 @@ are attributes-aware.
 Checking-out and checking-in
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Checking-out and checking-in
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

-The attribute `crlf` affects how the contents stored in the
+These attributes affect how the contents stored in the

 repository are copied to the working tree files when commands
 repository are copied to the working tree files when commands

-such as `git checkout` and `git merge` run.  It also affects how
+such as `git checkout` and `git merge` run.  They also affect how

 git stores the contents you prepare in the working tree in the
 repository upon `git add` and `git commit`.
 
 git stores the contents you prepare in the working tree in the
 repository upon `git add` and `git commit`.
 

+`crlf`
+^^^^^^
+
+This attribute controls the line-ending convention.
+

 Set::
 
        Setting the `crlf` attribute on a path is meant to mark
 Set::
 
        Setting the `crlf` attribute on a path is meant to mark


@@ -129,6 +134,28 @@ converted to LF upon checkin, but there is no conversion done
 upon checkout.
 
 
 upon checkout.
 
 

+`ident`
+^^^^^^^
+
+When the attribute `ident` is set to a path, git replaces
+`$ident$` in the blob object with `$ident:`, followed by
+40-character hexadecimal blob object name, followed by a dollar
+sign `$` upon checkout.  Any byte sequence that begins with
+`$ident:` and ends with `$` in the worktree file is replaced
+with `$ident$` upon check-in.
+
+
+Interaction between checkin/checkout attributes
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+In the check-in codepath, the worktree file is first converted
+with `ident` (if specified), and then with `crlf` (again, if
+specified and applicable).
+
+In the check-out codepath, the blob content is first converted
+with `crlf`, and then `ident`.
+
+

 Generating diff text
 ~~~~~~~~~~~~~~~~~~~~
 
 Generating diff text
 ~~~~~~~~~~~~~~~~~~~~
 

diff --git a/convert.c b/convert.c
index ad106ef35fb0729709b243d6292980f15cd1b0a5..5fdaee75714fa6a42601fbb366aeafb18f3334fb 100644 (file)
--- a/convert.c
+++ b/convert.c
@@ -1,5 +1,6 @@
 #include "cache.h"
 #include "attr.h"
 #include "cache.h"
 #include "attr.h"

+#include "run-command.h"

 
 /*
  * convert.c - convert a file when checking it out and checking it in.
 
 /*
  * convert.c - convert a file when checking it out and checking it in.


@@ -203,10 +204,152 @@ static char *crlf_to_worktree(const char *path, const char *src, unsigned long *
 static void setup_convert_check(struct git_attr_check *check)
 {
        static struct git_attr *attr_crlf;
 static void setup_convert_check(struct git_attr_check *check)
 {
        static struct git_attr *attr_crlf;

+       static struct git_attr *attr_ident;

 
 

-       if (!attr_crlf)
+       if (!attr_crlf) {

                attr_crlf = git_attr("crlf", 4);
                attr_crlf = git_attr("crlf", 4);

-       check->attr = attr_crlf;
+               attr_ident = git_attr("ident", 5);
+       }
+       check[0].attr = attr_crlf;
+       check[1].attr = attr_ident;
+}
+
+static int count_ident(const char *cp, unsigned long size)
+{
+       /*
+        * "$ident: 0000000000000000000000000000000000000000 $" <=> "$ident$"
+        */
+       int cnt = 0;
+       char ch;
+
+       while (size) {
+               ch = *cp++;
+               size--;
+               if (ch != '$')
+                       continue;
+               if (size < 6)
+                       break;
+               if (memcmp("ident", cp, 5))
+                       continue;
+               ch = cp[5];
+               cp += 6;
+               size -= 6;
+               if (ch == '$')
+                       cnt++; /* $ident$ */
+               if (ch != ':')
+                       continue;
+
+               /*
+                * "$ident: ... "; scan up to the closing dollar sign and discard.
+                */
+               while (size) {
+                       ch = *cp++;
+                       size--;
+                       if (ch == '$') {
+                               cnt++;
+                               break;
+                       }
+               }
+       }
+       return cnt;
+}
+
+static char *ident_to_git(const char *path, const char *src, unsigned long *sizep, int ident)
+{
+       int cnt;
+       unsigned long size;
+       char *dst, *buf;
+
+       if (!ident)
+               return NULL;
+       size = *sizep;
+       cnt = count_ident(src, size);
+       if (!cnt)
+               return NULL;
+       buf = xmalloc(size);
+
+       for (dst = buf; size; size--) {
+               char ch = *src++;
+               *dst++ = ch;
+               if ((ch == '$') && (6 <= size) &&
+                   !memcmp("ident:", src, 6)) {
+                       unsigned long rem = size - 6;
+                       const char *cp = src + 6;
+                       do {
+                               ch = *cp++;
+                               if (ch == '$')
+                                       break;
+                               rem--;
+                       } while (rem);
+                       if (!rem)
+                               continue;
+                       memcpy(dst, "ident$", 6);
+                       dst += 6;
+                       size -= (cp - src);
+                       src = cp;
+               }
+       }
+
+       *sizep = dst - buf;
+       return buf;
+}
+
+static char *ident_to_worktree(const char *path, const char *src, unsigned long *sizep, int ident)
+{
+       int cnt;
+       unsigned long size;
+       char *dst, *buf;
+       unsigned char sha1[20];
+
+       if (!ident)
+               return NULL;
+
+       size = *sizep;
+       cnt = count_ident(src, size);
+       if (!cnt)
+               return NULL;
+
+       hash_sha1_file(src, size, "blob", sha1);
+       buf = xmalloc(size + cnt * 43);
+
+       for (dst = buf; size; size--) {
+               const char *cp;
+               char ch = *src++;
+               *dst++ = ch;
+               if ((ch != '$') || (size < 6) || memcmp("ident", src, 5))
+                       continue;
+
+               if (src[5] == ':') {
+                       /* discard up to but not including the closing $ */
+                       unsigned long rem = size - 6;
+                       cp = src + 6;
+                       do {
+                               ch = *cp++;
+                               if (ch == '$')
+                                       break;
+                               rem--;
+                       } while (rem);
+                       if (!rem)
+                               continue;
+                       size -= (cp - src);
+               } else if (src[5] == '$')
+                       cp = src + 5;
+               else
+                       continue;
+
+               memcpy(dst, "ident: ", 7);
+               dst += 7;
+               memcpy(dst, sha1_to_hex(sha1), 40);
+               dst += 40;
+               *dst++ = ' ';
+               size -= (cp - src);
+               src = cp;
+               *dst++ = *src++;
+               size--;
+       }
+
+       *sizep = dst - buf;
+       return buf;

 }
 
 static int git_path_check_crlf(const char *path, struct git_attr_check *check)
 }
 
 static int git_path_check_crlf(const char *path, struct git_attr_check *check)


@@ -224,26 +367,57 @@ static int git_path_check_crlf(const char *path, struct git_attr_check *check)
        return CRLF_GUESS;
 }
 
        return CRLF_GUESS;
 }
 

+static int git_path_check_ident(const char *path, struct git_attr_check *check)
+{
+       const char *value = check->value;
+
+       return !!ATTR_TRUE(value);
+}
+

 char *convert_to_git(const char *path, const char *src, unsigned long *sizep)
 {
 char *convert_to_git(const char *path, const char *src, unsigned long *sizep)
 {

-       struct git_attr_check check[1];
+       struct git_attr_check check[2];

        int crlf = CRLF_GUESS;
        int crlf = CRLF_GUESS;

+       int ident = 0;
+       char *buf, *buf2;

 
        setup_convert_check(check);
 
        setup_convert_check(check);

-       if (!git_checkattr(path, 1, check)) {
-               crlf = git_path_check_crlf(path, check);
+       if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
+               crlf = git_path_check_crlf(path, check + 0);
+               ident = git_path_check_ident(path, check + 1);
+       }
+
+       buf = crlf_to_git(path, src, sizep, crlf);
+
+       buf2 = ident_to_git(path, buf ? buf : src, sizep, ident);
+       if (buf2) {
+               free(buf);
+               buf = buf2;

        }
        }

-       return crlf_to_git(path, src, sizep, crlf);
+
+       return buf;

 }
 
 char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep)
 {
 }
 
 char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep)
 {

-       struct git_attr_check check[1];
+       struct git_attr_check check[2];

        int crlf = CRLF_GUESS;
        int crlf = CRLF_GUESS;

+       int ident = 0;
+       char *buf, *buf2;

 
        setup_convert_check(check);
 
        setup_convert_check(check);

-       if (!git_checkattr(path, 1, check)) {
-               crlf = git_path_check_crlf(path, check);
+       if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
+               crlf = git_path_check_crlf(path, check + 0);
+               ident = git_path_check_ident(path, check + 1);

        }
        }

-       return crlf_to_worktree(path, src, sizep, crlf);
+
+       buf = ident_to_worktree(path, src, sizep, ident);
+
+       buf2 = crlf_to_worktree(path, buf ? buf : src, sizep, crlf);
+       if (buf2) {
+               free(buf);
+               buf = buf2;
+       }
+
+       return buf;

 }
 }

diff --git a/t/t0021-conversion.sh b/t/t0021-conversion.sh
new file mode 100755 (executable)
index 0000000..ad952c9
--- /dev/null
+++ b/t/t0021-conversion.sh
@@ -0,0 +1,39 @@
+#!/bin/sh
+
+test_description='blob conversion via gitattributes'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+       {
+           echo "*.i ident"
+       } >.gitattributes &&
+
+       {
+           echo a b c d e f g h i j k l m
+           echo n o p q r s t u v w x y z
+           echo '\''$ident$'\''
+       } >test &&
+       cat test >test.t &&
+       cat test >test.o &&
+       cat test >test.i &&
+       git add test test.t test.i &&
+       rm -f test test.t test.i &&
+       git checkout -- test test.t test.i
+'
+
+script='s/^\$ident: \([0-9a-f]*\) \$/\1/p'
+
+test_expect_success check '
+
+       cmp test.o test &&
+       cmp test.o test.t &&
+
+       # ident should be stripped in the repository
+       git diff --raw --exit-code :test :test.i &&
+       id=$(git rev-parse --verify :test) &&
+       embedded=$(sed -ne "$script" test.i) &&
+       test "z$id" = "z$embedded"
+'
+
+test_done