Merge branch 'en/fast-export-import'

Small fixes and features for fast-export and fast-import, mostly on
the fast-export side.

* en/fast-export-import:
  fast-export: add a --show-original-ids option to show original names
  fast-import: remove unmaintained duplicate documentation
  fast-export: add --reference-excluded-parents option
  fast-export: ensure we export requested refs
  fast-export: when using paths, avoid corrupt stream with non-existent mark
  fast-export: move commit rewriting logic into a function for reuse
  fast-export: avoid dying when filtering by paths and old tags exist
  fast-export: use value from correct enum
  git-fast-export.txt: clarify misleading documentation about rev-list args
  git-fast-import.txt: fix documentation for --quiet option
  fast-export: convert sha1 to oid
This commit is contained in:
Junio C Hamano
2019-01-04 13:33:33 -08:00
5 changed files with 268 additions and 214 deletions

View File

@ -1,157 +1,3 @@
/*
(See Documentation/git-fast-import.txt for maintained documentation.)
Format of STDIN stream:
stream ::= cmd*;
cmd ::= new_blob
| new_commit
| new_tag
| reset_branch
| checkpoint
| progress
;
new_blob ::= 'blob' lf
mark?
file_content;
file_content ::= data;
new_commit ::= 'commit' sp ref_str lf
mark?
('author' (sp name)? sp '<' email '>' sp when lf)?
'committer' (sp name)? sp '<' email '>' sp when lf
commit_msg
('from' sp commit-ish lf)?
('merge' sp commit-ish lf)*
(file_change | ls)*
lf?;
commit_msg ::= data;
ls ::= 'ls' sp '"' quoted(path) '"' lf;
file_change ::= file_clr
| file_del
| file_rnm
| file_cpy
| file_obm
| file_inm;
file_clr ::= 'deleteall' lf;
file_del ::= 'D' sp path_str lf;
file_rnm ::= 'R' sp path_str sp path_str lf;
file_cpy ::= 'C' sp path_str sp path_str lf;
file_obm ::= 'M' sp mode sp (hexsha1 | idnum) sp path_str lf;
file_inm ::= 'M' sp mode sp 'inline' sp path_str lf
data;
note_obm ::= 'N' sp (hexsha1 | idnum) sp commit-ish lf;
note_inm ::= 'N' sp 'inline' sp commit-ish lf
data;
new_tag ::= 'tag' sp tag_str lf
'from' sp commit-ish lf
('tagger' (sp name)? sp '<' email '>' sp when lf)?
tag_msg;
tag_msg ::= data;
reset_branch ::= 'reset' sp ref_str lf
('from' sp commit-ish lf)?
lf?;
checkpoint ::= 'checkpoint' lf
lf?;
progress ::= 'progress' sp not_lf* lf
lf?;
# note: the first idnum in a stream should be 1 and subsequent
# idnums should not have gaps between values as this will cause
# the stream parser to reserve space for the gapped values. An
# idnum can be updated in the future to a new object by issuing
# a new mark directive with the old idnum.
#
mark ::= 'mark' sp idnum lf;
data ::= (delimited_data | exact_data)
lf?;
# note: delim may be any string but must not contain lf.
# data_line may contain any data but must not be exactly
# delim.
delimited_data ::= 'data' sp '<<' delim lf
(data_line lf)*
delim lf;
# note: declen indicates the length of binary_data in bytes.
# declen does not include the lf preceding the binary data.
#
exact_data ::= 'data' sp declen lf
binary_data;
# note: quoted strings are C-style quoting supporting \c for
# common escapes of 'c' (e..g \n, \t, \\, \") or \nnn where nnn
# is the signed byte value in octal. Note that the only
# characters which must actually be escaped to protect the
# stream formatting is: \, " and LF. Otherwise these values
# are UTF8.
#
commit-ish ::= (ref_str | hexsha1 | sha1exp_str | idnum);
ref_str ::= ref;
sha1exp_str ::= sha1exp;
tag_str ::= tag;
path_str ::= path | '"' quoted(path) '"' ;
mode ::= '100644' | '644'
| '100755' | '755'
| '120000'
;
declen ::= # unsigned 32 bit value, ascii base10 notation;
bigint ::= # unsigned integer value, ascii base10 notation;
binary_data ::= # file content, not interpreted;
when ::= raw_when | rfc2822_when;
raw_when ::= ts sp tz;
rfc2822_when ::= # Valid RFC 2822 date and time;
sp ::= # ASCII space character;
lf ::= # ASCII newline (LF) character;
# note: a colon (':') must precede the numerical value assigned to
# an idnum. This is to distinguish it from a ref or tag name as
# GIT does not permit ':' in ref or tag strings.
#
idnum ::= ':' bigint;
path ::= # GIT style file path, e.g. "a/b/c";
ref ::= # GIT ref name, e.g. "refs/heads/MOZ_GECKO_EXPERIMENT";
tag ::= # GIT tag name, e.g. "FIREFOX_1_5";
sha1exp ::= # Any valid GIT SHA1 expression;
hexsha1 ::= # SHA1 in hexadecimal format;
# note: name and email are UTF8 strings, however name must not
# contain '<' or lf and email must not contain any of the
# following: '<', '>', lf.
#
name ::= # valid GIT author/committer name;
email ::= # valid GIT author/committer email;
ts ::= # time since the epoch in seconds, ascii base10 notation;
tz ::= # GIT style timezone;
# note: comments, get-mark, ls-tree, and cat-blob requests may
# appear anywhere in the input, except within a data command. Any
# form of the data command always escapes the related input from
# comment processing.
#
# In case it is not clear, the '#' that starts the comment
# must be the first character on that line (an lf
# preceded it).
#
get_mark ::= 'get-mark' sp idnum lf;
cat_blob ::= 'cat-blob' sp (hexsha1 | idnum) lf;
ls_tree ::= 'ls' sp (hexsha1 | idnum) sp path_str lf;
comment ::= '#' not_lf* lf;
not_lf ::= # Any byte that is not ASCII newline (LF);
*/
#include "builtin.h"
#include "cache.h"
#include "repository.h"
@ -1968,6 +1814,13 @@ static void parse_mark(void)
next_mark = 0;
}
static void parse_original_identifier(void)
{
const char *v;
if (skip_prefix(command_buf.buf, "original-oid ", &v))
read_next_command();
}
static int parse_data(struct strbuf *sb, uintmax_t limit, uintmax_t *len_res)
{
const char *data;
@ -2110,6 +1963,7 @@ static void parse_new_blob(void)
{
read_next_command();
parse_mark();
parse_original_identifier();
parse_and_store_blob(&last_blob, NULL, next_mark);
}
@ -2733,6 +2587,7 @@ static void parse_new_commit(const char *arg)
read_next_command();
parse_mark();
parse_original_identifier();
if (skip_prefix(command_buf.buf, "author ", &v)) {
author = parse_ident(v);
read_next_command();
@ -2865,6 +2720,9 @@ static void parse_new_tag(const char *arg)
die("Invalid ref name or SHA1 expression: %s", from);
read_next_command();
/* original-oid ... */
parse_original_identifier();
/* tagger ... */
if (skip_prefix(command_buf.buf, "tagger ", &v)) {
tagger = parse_ident(v);