You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

982 lines
21 KiB

/*
* GIT - The information manager from hell
*
* Copyright (C) Linus Torvalds, 2005
* Copyright (C) Johannes Schindelin, 2005
*
*/
#include "cache.h"
#define MAXNAME (256)
static FILE *config_file;
static const char *config_file_name;
static int config_linenr;
static int get_next_char(void)
{
int c;
FILE *f;
c = '\n';
if ((f = config_file) != NULL) {
c = fgetc(f);
if (c == '\r') {
/* DOS like systems */
c = fgetc(f);
if (c != '\n') {
ungetc(c, f);
c = '\r';
}
}
if (c == '\n')
config_linenr++;
if (c == EOF) {
config_file = NULL;
c = '\n';
}
}
return c;
}
static char *parse_value(void)
{
static char value[1024];
int quote = 0, comment = 0, len = 0, space = 0;
for (;;) {
int c = get_next_char();
if (len >= sizeof(value))
return NULL;
if (c == '\n') {
if (quote)
return NULL;
value[len] = 0;
return value;
}
if (comment)
continue;
if (isspace(c) && !quote) {
space = 1;
continue;
}
if (!quote) {
if (c == ';' || c == '#') {
comment = 1;
continue;
}
}
if (space) {
if (len)
value[len++] = ' ';
space = 0;
}
if (c == '\\') {
c = get_next_char();
switch (c) {
case '\n':
continue;
case 't':
c = '\t';
break;
case 'b':
c = '\b';
break;
case 'n':
c = '\n';
break;
/* Some characters escape as themselves */
case '\\': case '"':
break;
/* Reject unknown escape sequences */
default:
return NULL;
}
value[len++] = c;
continue;
}
if (c == '"') {
quote = 1-quote;
continue;
}
value[len++] = c;
}
}
static inline int iskeychar(int c)
{
return isalnum(c) || c == '-';
}
static int get_value(config_fn_t fn, char *name, unsigned int len)
{
int c;
char *value;
/* Get the full name */
for (;;) {
c = get_next_char();
if (c == EOF)
break;
if (!iskeychar(c))
break;
name[len++] = tolower(c);
if (len >= MAXNAME)
return -1;
}
name[len] = 0;
while (c == ' ' || c == '\t')
c = get_next_char();
value = NULL;
if (c != '\n') {
if (c != '=')
return -1;
value = parse_value();
if (!value)
return -1;
}
return fn(name, value);
}
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
static int get_extended_base_var(char *name, int baselen, int c)
{
do {
if (c == '\n')
return -1;
c = get_next_char();
} while (isspace(c));
/* We require the format to be '[base "extension"]' */
if (c != '"')
return -1;
name[baselen++] = '.';
for (;;) {
int c = get_next_char();
if (c == '\n')
return -1;
if (c == '"')
break;
if (c == '\\') {
c = get_next_char();
if (c == '\n')
return -1;
}
name[baselen++] = c;
if (baselen > MAXNAME / 2)
return -1;
}
/* Final ']' */
if (get_next_char() != ']')
return -1;
return baselen;
}
static int get_base_var(char *name)
{
int baselen = 0;
for (;;) {
int c = get_next_char();
if (c == EOF)
return -1;
if (c == ']')
return baselen;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
if (isspace(c))
return get_extended_base_var(name, baselen, c);
if (!iskeychar(c) && c != '.')
return -1;
if (baselen > MAXNAME / 2)
return -1;
name[baselen++] = tolower(c);
}
}
static int git_parse_file(config_fn_t fn)
{
int comment = 0;
int baselen = 0;
static char var[MAXNAME];
for (;;) {
int c = get_next_char();
if (c == '\n') {
/* EOF? */
if (!config_file)
return 0;
comment = 0;
continue;
}
if (comment || isspace(c))
continue;
if (c == '#' || c == ';') {
comment = 1;
continue;
}
if (c == '[') {
baselen = get_base_var(var);
if (baselen <= 0)
break;
var[baselen++] = '.';
var[baselen] = 0;
continue;
}
if (!isalpha(c))
break;
var[baselen] = tolower(c);
if (get_value(fn, var, baselen+1) < 0)
break;
}
die("bad config file line %d in %s", config_linenr, config_file_name);
}
int git_config_int(const char *name, const char *value)
{
if (value && *value) {
char *end;
int val = strtol(value, &end, 0);
if (!*end)
return val;
if (!strcasecmp(end, "k"))
return val * 1024;
if (!strcasecmp(end, "m"))
return val * 1024 * 1024;
if (!strcasecmp(end, "g"))
return val * 1024 * 1024 * 1024;
}
die("bad config value for '%s' in %s", name, config_file_name);
}
int git_config_bool(const char *name, const char *value)
{
if (!value)
return 1;
if (!*value)
return 0;
if (!strcasecmp(value, "true") || !strcasecmp(value, "yes"))
return 1;
if (!strcasecmp(value, "false") || !strcasecmp(value, "no"))
return 0;
return git_config_int(name, value) != 0;
}
int git_default_config(const char *var, const char *value)
{
/* This needs a better name */
if (!strcmp(var, "core.filemode")) {
trust_executable_bit = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.symlinks")) {
has_symlinks = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.bare")) {
is_bare_repository_cfg = git_config_bool(var, value);
return 0;
}
"Assume unchanged" git This adds "assume unchanged" logic, started by this message in the list discussion recently: <Pine.LNX.4.64.0601311807470.7301@g5.osdl.org> This is a workaround for filesystems that do not have lstat() that is quick enough for the index mechanism to take advantage of. On the paths marked as "assumed to be unchanged", the user needs to explicitly use update-index to register the object name to be in the next commit. You can use two new options to update-index to set and reset the CE_VALID bit: git-update-index --assume-unchanged path... git-update-index --no-assume-unchanged path... These forms manipulate only the CE_VALID bit; it does not change the object name recorded in the index file. Nor they add a new entry to the index. When the configuration variable "core.ignorestat = true" is set, the index entries are marked with CE_VALID bit automatically after: - update-index to explicitly register the current object name to the index file. - when update-index --refresh finds the path to be up-to-date. - when tools like read-tree -u and apply --index update the working tree file and register the current object name to the index file. The flag is dropped upon read-tree that does not check out the index entry. This happens regardless of the core.ignorestat settings. Index entries marked with CE_VALID bit are assumed to be unchanged most of the time. However, there are cases that CE_VALID bit is ignored for the sake of safety and usability: - while "git-read-tree -m" or git-apply need to make sure that the paths involved in the merge do not have local modifications. This sacrifices performance for safety. - when git-checkout-index -f -q -u -a tries to see if it needs to checkout the paths. Otherwise you can never check anything out ;-). - when git-update-index --really-refresh (a new flag) tries to see if the index entry is up to date. You can start with everything marked as CE_VALID and run this once to drop CE_VALID bit for paths that are modified. Most notably, "update-index --refresh" honours CE_VALID and does not actively stat, so after you modified a file in the working tree, update-index --refresh would not notice until you tell the index about it with "git-update-index path" or "git-update-index --no-assume-unchanged path". This version is not expected to be perfect. I think diff between index and/or tree and working files may need some adjustment, and there probably needs other cases we should automatically unmark paths that are marked to be CE_VALID. But the basics seem to work, and ready to be tested by people who asked for this feature. Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
if (!strcmp(var, "core.ignorestat")) {
assume_unchanged = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.prefersymlinkrefs")) {
prefer_symlink_refs = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.logallrefupdates")) {
log_all_ref_updates = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.warnambiguousrefs")) {
warn_ambiguous_refs = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.legacyheaders")) {
use_legacy_headers = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "core.compression")) {
int level = git_config_int(var, value);
if (level == -1)
level = Z_DEFAULT_COMPRESSION;
else if (level < 0 || level > Z_BEST_COMPRESSION)
die("bad zlib compression level %d", level);
zlib_compression_level = level;
return 0;
}
Fully activate the sliding window pack access. This finally turns on the sliding window behavior for packfile data access by mapping limited size windows and chaining them under the packed_git->windows list. We consider a given byte offset to be within the window only if there would be at least 20 bytes (one hash worth of data) accessible after the requested offset. This range selection relates to the contract that use_pack() makes with its callers, allowing them to access one hash or one object header without needing to call use_pack() for every byte of data obtained. In the worst case scenario we will map the same page of data twice into memory: once at the end of one window and once again at the start of the next window. This duplicate page mapping will happen only when an object header or a delta base reference is spanned over the end of a window and is always limited to just one page of duplication, as no sane operating system will ever have a page size smaller than a hash. I am assuming that the possible wasted page of virtual address space is going to perform faster than the alternatives, which would be to copy the object header or ref delta into a temporary buffer prior to parsing, or to check the window range on every byte during header parsing. We may decide to revisit this decision in the future since this is just a gut instinct decision and has not actually been proven out by experimental testing. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
18 years ago
if (!strcmp(var, "core.packedgitwindowsize")) {
int pgsz_x2 = getpagesize() * 2;
Fully activate the sliding window pack access. This finally turns on the sliding window behavior for packfile data access by mapping limited size windows and chaining them under the packed_git->windows list. We consider a given byte offset to be within the window only if there would be at least 20 bytes (one hash worth of data) accessible after the requested offset. This range selection relates to the contract that use_pack() makes with its callers, allowing them to access one hash or one object header without needing to call use_pack() for every byte of data obtained. In the worst case scenario we will map the same page of data twice into memory: once at the end of one window and once again at the start of the next window. This duplicate page mapping will happen only when an object header or a delta base reference is spanned over the end of a window and is always limited to just one page of duplication, as no sane operating system will ever have a page size smaller than a hash. I am assuming that the possible wasted page of virtual address space is going to perform faster than the alternatives, which would be to copy the object header or ref delta into a temporary buffer prior to parsing, or to check the window range on every byte during header parsing. We may decide to revisit this decision in the future since this is just a gut instinct decision and has not actually been proven out by experimental testing. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
18 years ago
packed_git_window_size = git_config_int(var, value);
/* This value must be multiple of (pagesize * 2) */
packed_git_window_size /= pgsz_x2;
if (packed_git_window_size < 1)
packed_git_window_size = 1;
packed_git_window_size *= pgsz_x2;
Fully activate the sliding window pack access. This finally turns on the sliding window behavior for packfile data access by mapping limited size windows and chaining them under the packed_git->windows list. We consider a given byte offset to be within the window only if there would be at least 20 bytes (one hash worth of data) accessible after the requested offset. This range selection relates to the contract that use_pack() makes with its callers, allowing them to access one hash or one object header without needing to call use_pack() for every byte of data obtained. In the worst case scenario we will map the same page of data twice into memory: once at the end of one window and once again at the start of the next window. This duplicate page mapping will happen only when an object header or a delta base reference is spanned over the end of a window and is always limited to just one page of duplication, as no sane operating system will ever have a page size smaller than a hash. I am assuming that the possible wasted page of virtual address space is going to perform faster than the alternatives, which would be to copy the object header or ref delta into a temporary buffer prior to parsing, or to check the window range on every byte during header parsing. We may decide to revisit this decision in the future since this is just a gut instinct decision and has not actually been proven out by experimental testing. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
18 years ago
return 0;
}
if (!strcmp(var, "core.packedgitlimit")) {
packed_git_limit = git_config_int(var, value);
return 0;
}
if (!strcmp(var, "core.deltabasecachelimit")) {
delta_base_cache_limit = git_config_int(var, value);
return 0;
}
Lazy man's auto-CRLF It currently does NOT know about file attributes, so it does its conversion purely based on content. Maybe that is more in the "git philosophy" anyway, since content is king, but I think we should try to do the file attributes to turn it off on demand. Anyway, BY DEFAULT it is off regardless, because it requires a [core] AutoCRLF = true in your config file to be enabled. We could make that the default for Windows, of course, the same way we do some other things (filemode etc). But you can actually enable it on UNIX, and it will cause: - "git update-index" will write blobs without CRLF - "git diff" will diff working tree files without CRLF - "git checkout" will write files to the working tree _with_ CRLF and things work fine. Funnily, it actually shows an odd file in git itself: git clone -n git test-crlf cd test-crlf git config core.autocrlf true git checkout git diff shows a diff for "Documentation/docbook-xsl.css". Why? Because we have actually checked in that file *with* CRLF! So when "core.autocrlf" is true, we'll always generate a *different* hash for it in the index, because the index hash will be for the content _without_ CRLF. Is this complete? I dunno. It seems to work for me. It doesn't use the filename at all right now, and that's probably a deficiency (we could certainly make the "is_binary()" heuristics also take standard filename heuristics into account). I don't pass in the filename at all for the "index_fd()" case (git-update-index), so that would need to be passed around, but this actually works fine. NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours truly. I will not guarantee that they work at all reasonable. Caveat emptor. But it _is_ simple, and it _is_ safe, since it's all off by default. The patch is pretty simple - the biggest part is the new "convert.c" file, but even that is really just basic stuff that anybody can write in "Teaching C 101" as a final project for their first class in programming. Not to say that it's bug-free, of course - but at least we're not talking about rocket surgery here. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
18 years ago
if (!strcmp(var, "core.autocrlf")) {
if (value && !strcasecmp(value, "input")) {
auto_crlf = -1;
return 0;
}
Lazy man's auto-CRLF It currently does NOT know about file attributes, so it does its conversion purely based on content. Maybe that is more in the "git philosophy" anyway, since content is king, but I think we should try to do the file attributes to turn it off on demand. Anyway, BY DEFAULT it is off regardless, because it requires a [core] AutoCRLF = true in your config file to be enabled. We could make that the default for Windows, of course, the same way we do some other things (filemode etc). But you can actually enable it on UNIX, and it will cause: - "git update-index" will write blobs without CRLF - "git diff" will diff working tree files without CRLF - "git checkout" will write files to the working tree _with_ CRLF and things work fine. Funnily, it actually shows an odd file in git itself: git clone -n git test-crlf cd test-crlf git config core.autocrlf true git checkout git diff shows a diff for "Documentation/docbook-xsl.css". Why? Because we have actually checked in that file *with* CRLF! So when "core.autocrlf" is true, we'll always generate a *different* hash for it in the index, because the index hash will be for the content _without_ CRLF. Is this complete? I dunno. It seems to work for me. It doesn't use the filename at all right now, and that's probably a deficiency (we could certainly make the "is_binary()" heuristics also take standard filename heuristics into account). I don't pass in the filename at all for the "index_fd()" case (git-update-index), so that would need to be passed around, but this actually works fine. NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours truly. I will not guarantee that they work at all reasonable. Caveat emptor. But it _is_ simple, and it _is_ safe, since it's all off by default. The patch is pretty simple - the biggest part is the new "convert.c" file, but even that is really just basic stuff that anybody can write in "Teaching C 101" as a final project for their first class in programming. Not to say that it's bug-free, of course - but at least we're not talking about rocket surgery here. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
18 years ago
auto_crlf = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "user.name")) {
strlcpy(git_default_name, value, sizeof(git_default_name));
return 0;
}
if (!strcmp(var, "user.email")) {
strlcpy(git_default_email, value, sizeof(git_default_email));
return 0;
}
if (!strcmp(var, "i18n.commitencoding")) {
git_commit_encoding = xstrdup(value);
return 0;
}
if (!strcmp(var, "i18n.logoutputencoding")) {
git_log_output_encoding = xstrdup(value);
return 0;
}
if (!strcmp(var, "pager.color") || !strcmp(var, "color.pager")) {
pager_use_color = git_config_bool(var,value);
return 0;
}
/* Add other config variables here and to Documentation/config.txt. */
return 0;
}
int git_config_from_file(config_fn_t fn, const char *filename)
{
int ret;
FILE *f = fopen(filename, "r");
ret = -1;
if (f) {
config_file = f;
config_file_name = filename;
config_linenr = 1;
ret = git_parse_file(fn);
fclose(f);
config_file_name = NULL;
}
return ret;
}
int git_config(config_fn_t fn)
{
int ret = 0;
char *repo_config = NULL;
const char *home = NULL, *filename;
/* $GIT_CONFIG makes git read _only_ the given config file,
* $GIT_CONFIG_LOCAL will make it process it in addition to the
* global config file, the same way it would the per-repository
* config file otherwise. */
filename = getenv(CONFIG_ENVIRONMENT);
if (!filename) {
if (!access(ETC_GITCONFIG, R_OK))
ret += git_config_from_file(fn, ETC_GITCONFIG);
home = getenv("HOME");
filename = getenv(CONFIG_LOCAL_ENVIRONMENT);
if (!filename)
filename = repo_config = xstrdup(git_path("config"));
}
if (home) {
char *user_config = xstrdup(mkpath("%s/.gitconfig", home));
if (!access(user_config, R_OK))
ret = git_config_from_file(fn, user_config);
free(user_config);
}
ret += git_config_from_file(fn, filename);
free(repo_config);
return ret;
}
/*
* Find all the stuff for git_config_set() below.
*/
#define MAX_MATCHES 512
static struct {
int baselen;
char* key;
int do_not_match;
regex_t* value_regex;
int multi_replace;
size_t offset[MAX_MATCHES];
enum { START, SECTION_SEEN, SECTION_END_SEEN, KEY_SEEN } state;
int seen;
} store;
static int matches(const char* key, const char* value)
{
return !strcmp(key, store.key) &&
(store.value_regex == NULL ||
(store.do_not_match ^
!regexec(store.value_regex, value, 0, NULL, 0)));
}
static int store_aux(const char* key, const char* value)
{
const char *ep;
size_t section_len;
switch (store.state) {
case KEY_SEEN:
if (matches(key, value)) {
if (store.seen == 1 && store.multi_replace == 0) {
fprintf(stderr,
"Warning: %s has multiple values\n",
key);
} else if (store.seen >= MAX_MATCHES) {
fprintf(stderr, "Too many matches\n");
return 1;
}
store.offset[store.seen] = ftell(config_file);
store.seen++;
}
break;
case SECTION_SEEN:
/*
* What we are looking for is in store.key (both
* section and var), and its section part is baselen
* long. We found key (again, both section and var).
* We would want to know if this key is in the same
* section as what we are looking for. We already
* know we are in the same section as what should
* hold store.key.
*/
ep = strrchr(key, '.');
section_len = ep - key;
if ((section_len != store.baselen) ||
memcmp(key, store.key, section_len+1)) {
store.state = SECTION_END_SEEN;
break;
}
/*
* Do not increment matches: this is no match, but we
* just made sure we are in the desired section.
*/
store.offset[store.seen] = ftell(config_file);
/* fallthru */
case SECTION_END_SEEN:
case START:
if (matches(key, value)) {
store.offset[store.seen] = ftell(config_file);
store.state = KEY_SEEN;
store.seen++;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
} else {
if (strrchr(key, '.') - key == store.baselen &&
!strncmp(key, store.key, store.baselen)) {
store.state = SECTION_SEEN;
store.offset[store.seen] = ftell(config_file);
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
}
}
}
return 0;
}
static int write_error()
{
fprintf(stderr, "Failed to write new configuration file\n");
/* Same error code as "failed to rename". */
return 4;
}
static int store_write_section(int fd, const char* key)
{
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
const char *dot = strchr(key, '.');
int len1 = store.baselen, len2 = -1;
dot = strchr(key, '.');
if (dot) {
int dotlen = dot - key;
if (dotlen < len1) {
len2 = len1 - dotlen - 1;
len1 = dotlen;
}
}
if (write_in_full(fd, "[", 1) != 1 ||
write_in_full(fd, key, len1) != len1)
return 0;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
if (len2 >= 0) {
if (write_in_full(fd, " \"", 2) != 2)
return 0;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
while (--len2 >= 0) {
unsigned char c = *++dot;
if (c == '"')
if (write_in_full(fd, "\\", 1) != 1)
return 0;
if (write_in_full(fd, &c, 1) != 1)
return 0;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
}
if (write_in_full(fd, "\"", 1) != 1)
return 0;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
}
if (write_in_full(fd, "]\n", 2) != 2)
return 0;
return 1;
}
static int store_write_pair(int fd, const char* key, const char* value)
{
int i;
int length = strlen(key+store.baselen+1);
int quote = 0;
/* Check to see if the value needs to be quoted. */
if (value[0] == ' ')
quote = 1;
for (i = 0; value[i]; i++)
if (value[i] == ';' || value[i] == '#')
quote = 1;
if (value[i-1] == ' ')
quote = 1;
if (write_in_full(fd, "\t", 1) != 1 ||
write_in_full(fd, key+store.baselen+1, length) != length ||
write_in_full(fd, " = ", 3) != 3)
return 0;
if (quote && write_in_full(fd, "\"", 1) != 1)
return 0;
for (i = 0; value[i]; i++)
switch (value[i]) {
case '\n':
if (write_in_full(fd, "\\n", 2) != 2)
return 0;
break;
case '\t':
if (write_in_full(fd, "\\t", 2) != 2)
return 0;
break;
case '"':
case '\\':
if (write_in_full(fd, "\\", 1) != 1)
return 0;
default:
if (write_in_full(fd, value+i, 1) != 1)
return 0;
break;
}
if (quote && write_in_full(fd, "\"", 1) != 1)
return 0;
if (write_in_full(fd, "\n", 1) != 1)
return 0;
return 1;
}
static ssize_t find_beginning_of_line(const char* contents, size_t size,
size_t offset_, int* found_bracket)
{
size_t equal_offset = size, bracket_offset = size;
ssize_t offset;
for (offset = offset_-2; offset > 0
&& contents[offset] != '\n'; offset--)
switch (contents[offset]) {
case '=': equal_offset = offset; break;
case ']': bracket_offset = offset; break;
}
if (bracket_offset < equal_offset) {
*found_bracket = 1;
offset = bracket_offset+1;
} else
offset++;
return offset;
}
int git_config_set(const char* key, const char* value)
{
return git_config_set_multivar(key, value, NULL, 0);
}
/*
* If value==NULL, unset in (remove from) config,
* if value_regex!=NULL, disregard key/value pairs where value does not match.
* if multi_replace==0, nothing, or only one matching key/value is replaced,
* else all matching key/values (regardless how many) are removed,
* before the new pair is written.
*
* Returns 0 on success.
*
* This function does this:
*
* - it locks the config file by creating ".git/config.lock"
*
* - it then parses the config using store_aux() as validator to find
* the position on the key/value pair to replace. If it is to be unset,
* it must be found exactly once.
*
* - the config file is mmap()ed and the part before the match (if any) is
* written to the lock file, then the changed part and the rest.
*
* - the config file is removed and the lock file rename()d to it.
*
*/
int git_config_set_multivar(const char* key, const char* value,
const char* value_regex, int multi_replace)
{
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
int i, dot;
int fd = -1, in_fd;
int ret;
char* config_filename;
char* lock_file;
const char* last_dot = strrchr(key, '.');
config_filename = getenv(CONFIG_ENVIRONMENT);
if (!config_filename) {
config_filename = getenv(CONFIG_LOCAL_ENVIRONMENT);
if (!config_filename)
config_filename = git_path("config");
}
config_filename = xstrdup(config_filename);
lock_file = xstrdup(mkpath("%s.lock", config_filename));
/*
* Since "key" actually contains the section name and the real
* key name separated by a dot, we have to know where the dot is.
*/
if (last_dot == NULL) {
fprintf(stderr, "key does not contain a section: %s\n", key);
ret = 2;
goto out_free;
}
store.baselen = last_dot - key;
store.multi_replace = multi_replace;
/*
* Validate the key and while at it, lower case it for matching.
*/
store.key = xmalloc(strlen(key) + 1);
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
dot = 0;
for (i = 0; key[i]; i++) {
unsigned char c = key[i];
if (c == '.')
dot = 1;
/* Leave the extended basename untouched.. */
if (!dot || i > store.baselen) {
if (!iskeychar(c) || (i == store.baselen+1 && !isalpha(c))) {
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
fprintf(stderr, "invalid key: %s\n", key);
free(store.key);
ret = 1;
goto out_free;
}
c = tolower(c);
} else if (c == '\n') {
fprintf(stderr, "invalid key (newline): %s\n", key);
free(store.key);
ret = 1;
goto out_free;
git config syntax updates This updates the hierarchical section name syntax to [section<space>+"<randomstring>"] where the only rule for "randomstring" is that it can't contain a newline, and if you really want to insert a double-quote, you do it with \". It turns that into the section name "secion.randomstring". The "section" part is still case insensitive, but the "randomstring" part is case sensitive. So you could use this for things like [email "torvalds@osdl.org"] name = Linus Torvalds if you wanted to do the "email->name" conversion as part of the config file format (I'm not claiming that is sensible, I'm just giving it as an insane example). That would show up as the association email.torvalds@osdl.org.name -> Linus Torvalds which is easy to parse (the "." in the email _looks_ ambiguous, but it isn't: you know that there will always be a single key-name, so you find the key name with "strrchr(name, '.')" and things are entirely unambiguous). Repo-config is updated to be able to parse the new format, and also write things out in the new format. [jc: rolled two patches from Linus and one fix-up from Sean into one, with additional adjustments for t/t1300 test to check the case insensitiveness of section base and variable and case sensitiveness of the extended section part. Then stripped some part off to make the result applicable to the stale 1.3.X series that does not have recent enhancements. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Sean Estabrooks <seanlkml@sympatico.ca> Signed-off-by: Junio C Hamano <junkio@cox.net>
19 years ago
}
store.key[i] = c;
}
store.key[i] = 0;
/*
* The lock_file serves a purpose in addition to locking: the new
* contents of .git/config will be written into it.
*/
fd = open(lock_file, O_WRONLY | O_CREAT | O_EXCL, 0666);
if (fd < 0 || adjust_shared_perm(lock_file)) {
fprintf(stderr, "could not lock config file\n");
free(store.key);
ret = -1;
goto out_free;
}
/*
* If .git/config does not exist yet, write a minimal version.
*/
in_fd = open(config_filename, O_RDONLY);
if ( in_fd < 0 ) {
free(store.key);
if ( ENOENT != errno ) {
error("opening %s: %s", config_filename,
strerror(errno));
ret = 3; /* same as "invalid config file" */
goto out_free;
}
/* if nothing to unset, error out */
if (value == NULL) {
ret = 5;
goto out_free;
}
store.key = (char*)key;
if (!store_write_section(fd, key) ||
!store_write_pair(fd, key, value))
goto write_err_out;
} else {
struct stat st;
char* contents;
size_t contents_sz, copy_begin, copy_end;
int i, new_line = 0;
if (value_regex == NULL)
store.value_regex = NULL;
else {
if (value_regex[0] == '!') {
store.do_not_match = 1;
value_regex++;
} else
store.do_not_match = 0;
store.value_regex = (regex_t*)xmalloc(sizeof(regex_t));
if (regcomp(store.value_regex, value_regex,
REG_EXTENDED)) {
fprintf(stderr, "Invalid pattern: %s\n",
value_regex);
free(store.value_regex);
ret = 6;
goto out_free;
}
}
store.offset[0] = 0;
store.state = START;
store.seen = 0;
/*
* After this, store.offset will contain the *end* offset
* of the last match, or remain at 0 if no match was found.
* As a side effect, we make sure to transform only a valid
* existing config file.
*/
if (git_config_from_file(store_aux, config_filename)) {
fprintf(stderr, "invalid config file\n");
free(store.key);
if (store.value_regex != NULL) {
regfree(store.value_regex);
free(store.value_regex);
}
ret = 3;
goto out_free;
}
free(store.key);
if (store.value_regex != NULL) {
regfree(store.value_regex);
free(store.value_regex);
}
/* if nothing to unset, or too many matches, error out */
if ((store.seen == 0 && value == NULL) ||
(store.seen > 1 && multi_replace == 0)) {
ret = 5;
goto out_free;
}
fstat(in_fd, &st);
contents_sz = xsize_t(st.st_size);
contents = xmmap(NULL, contents_sz, PROT_READ,
MAP_PRIVATE, in_fd, 0);
close(in_fd);
if (store.seen == 0)
store.seen = 1;
for (i = 0, copy_begin = 0; i < store.seen; i++) {
if (store.offset[i] == 0) {
store.offset[i] = copy_end = contents_sz;
} else if (store.state != KEY_SEEN) {
copy_end = store.offset[i];
} else
copy_end = find_beginning_of_line(
contents, contents_sz,
store.offset[i]-2, &new_line);
/* write the first part of the config */
if (copy_end > copy_begin) {
if (write_in_full(fd, contents + copy_begin,
copy_end - copy_begin) <
copy_end - copy_begin)
goto write_err_out;
if (new_line &&
write_in_full(fd, "\n", 1) != 1)
goto write_err_out;
}
copy_begin = store.offset[i];
}
/* write the pair (value == NULL means unset) */
if (value != NULL) {
if (store.state == START) {
if (!store_write_section(fd, key))
goto write_err_out;
}
if (!store_write_pair(fd, key, value))
goto write_err_out;
}
/* write the rest of the config */
if (copy_begin < contents_sz)
if (write_in_full(fd, contents + copy_begin,
contents_sz - copy_begin) <
contents_sz - copy_begin)
goto write_err_out;
munmap(contents, contents_sz);
unlink(config_filename);
}
if (rename(lock_file, config_filename) < 0) {
fprintf(stderr, "Could not rename the lock file?\n");
ret = 4;
goto out_free;
}
ret = 0;
out_free:
if (0 <= fd)
close(fd);
free(config_filename);
if (lock_file) {
unlink(lock_file);
free(lock_file);
}
return ret;
write_err_out:
ret = write_error();
goto out_free;
}
static int section_name_match (const char *buf, const char *name)
{
int i = 0, j = 0, dot = 0;
for (; buf[i] && buf[i] != ']'; i++) {
if (!dot && isspace(buf[i])) {
dot = 1;
if (name[j++] != '.')
break;
for (i++; isspace(buf[i]); i++)
; /* do nothing */
if (buf[i] != '"')
break;
continue;
}
if (buf[i] == '\\' && dot)
i++;
else if (buf[i] == '"' && dot) {
for (i++; isspace(buf[i]); i++)
; /* do_nothing */
break;
}
if (buf[i] != name[j++])
break;
}
return (buf[i] == ']' && name[j] == 0);
}
/* if new_name == NULL, the section is removed instead */
int git_config_rename_section(const char *old_name, const char *new_name)
{
int ret = 0, remove = 0;
char *config_filename;
struct lock_file *lock = xcalloc(sizeof(struct lock_file), 1);
int out_fd;
char buf[1024];
config_filename = getenv(CONFIG_ENVIRONMENT);
if (!config_filename) {
config_filename = getenv(CONFIG_LOCAL_ENVIRONMENT);
if (!config_filename)
config_filename = git_path("config");
}
config_filename = xstrdup(config_filename);
out_fd = hold_lock_file_for_update(lock, config_filename, 0);
if (out_fd < 0) {
ret = error("Could not lock config file!");
goto out;
}
if (!(config_file = fopen(config_filename, "rb"))) {
/* no config file means nothing to rename, no error */
goto unlock_and_out;
}
while (fgets(buf, sizeof(buf), config_file)) {
int i;
int length;
for (i = 0; buf[i] && isspace(buf[i]); i++)
; /* do nothing */
if (buf[i] == '[') {
/* it's a section */
if (section_name_match (&buf[i+1], old_name)) {
ret++;
if (new_name == NULL) {
remove = 1;
continue;
}
store.baselen = strlen(new_name);
if (!store_write_section(out_fd, new_name)) {
ret = write_error();
goto out;
}
continue;
}
remove = 0;
}
if (remove)
continue;
length = strlen(buf);
if (write_in_full(out_fd, buf, length) != length) {
ret = write_error();
goto out;
}
}
fclose(config_file);
unlock_and_out:
if (close(out_fd) || commit_lock_file(lock) < 0)
ret = error("Cannot commit config file!");
out:
free(config_filename);
return ret;
}