summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--.gitignore1
-rw-r--r--Documentation/config.txt45
-rw-r--r--Documentation/git-config.txt29
-rw-r--r--Makefile3
-rw-r--r--builtin/config.c140
-rw-r--r--http.c16
-rw-r--r--t/.gitattributes1
-rwxr-xr-xt/t0110-urlmatch-normalization.sh177
-rw-r--r--t/t0110/README9
-rw-r--r--t/t0110/url-11
-rw-r--r--t/t0110/url-101
-rw-r--r--t/t0110/url-111
-rw-r--r--t/t0110/url-21
-rw-r--r--t/t0110/url-31
-rw-r--r--t/t0110/url-41
-rw-r--r--t/t0110/url-51
-rw-r--r--t/t0110/url-61
-rw-r--r--t/t0110/url-71
-rw-r--r--t/t0110/url-81
-rw-r--r--t/t0110/url-91
-rwxr-xr-xt/t1300-repo-config.sh25
-rw-r--r--test-urlmatch-normalization.c50
-rw-r--r--urlmatch.c535
-rw-r--r--urlmatch.h54
24 files changed, 1072 insertions, 24 deletions
diff --git a/.gitignore b/.gitignore
index 6b1fd1bfb0..66199edd4a 100644
--- a/.gitignore
+++ b/.gitignore
@@ -202,6 +202,7 @@
/test-string-list
/test-subprocess
/test-svn-fe
+/test-urlmatch-normalization
/test-wildmatch
/common-cmds.h
*.tar.gz
diff --git a/Documentation/config.txt b/Documentation/config.txt
index e8eadde305..00bde9dec5 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1533,6 +1533,51 @@ http.useragent::
of common USER_AGENT strings (but not including those like git/1.7.1).
Can be overridden by the 'GIT_HTTP_USER_AGENT' environment variable.
+http.<url>.*::
+ Any of the http.* options above can be applied selectively to some urls.
+ For a config key to match a URL, each element of the config key is
+ compared to that of the URL, in the following order:
++
+--
+. Scheme (e.g., `https` in `https://example.com/`). This field
+ must match exactly between the config key and the URL.
+
+. Host/domain name (e.g., `example.com` in `https://example.com/`).
+ This field must match exactly between the config key and the URL.
+
+. Port number (e.g., `8080` in `http://example.com:8080/`).
+ This field must match exactly between the config key and the URL.
+ Omitted port numbers are automatically converted to the correct
+ default for the scheme before matching.
+
+. Path (e.g., `repo.git` in `https://example.com/repo.git`). The
+ path field of the config key must match the path field of the URL
+ either exactly or as a prefix of slash-delimited path elements. This means
+ a config key with path `foo/` matches URL path `foo/bar`. A prefix can only
+ match on a slash (`/`) boundary. Longer matches take precedence (so a config
+ key with path `foo/bar` is a better match to URL path `foo/bar` than a config
+ key with just path `foo/`).
+
+. User name (e.g., `user` in `https://user@example.com/repo.git`). If
+ the config key has a user name it must match the user name in the
+ URL exactly. If the config key does not have a user name, that
+ config key will match a URL with any user name (including none),
+ but at a lower precedence than a config key with a user name.
+--
++
+The list above is ordered by decreasing precedence; a URL that matches
+a config key's path is preferred to one that matches its user name. For example,
+if the URL is `https://user@example.com/foo/bar` a config key match of
+`https://example.com/foo` will be preferred over a config key match of
+`https://user@example.com`.
++
+All URLs are normalized before attempting any matching (the password part,
+if embedded in the URL, is always ignored for matching purposes) so that
+equivalent urls that are simply spelled differently will match properly.
+Environment variable settings always override any matches. The urls that are
+matched against are those given directly to Git commands. This means any URLs
+visited as a result of a redirection do not participate in matching.
+
i18n.commitEncoding::
Character encoding the commit messages are stored in; Git itself
does not care per se, but this information is necessary e.g. when
diff --git a/Documentation/git-config.txt b/Documentation/git-config.txt
index 2dbe486eb1..e9917b89a9 100644
--- a/Documentation/git-config.txt
+++ b/Documentation/git-config.txt
@@ -15,6 +15,7 @@ SYNOPSIS
'git config' [<file-option>] [type] [-z|--null] --get name [value_regex]
'git config' [<file-option>] [type] [-z|--null] --get-all name [value_regex]
'git config' [<file-option>] [type] [-z|--null] --get-regexp name_regex [value_regex]
+'git config' [<file-option>] [type] [-z|--null] --get-urlmatch name URL
'git config' [<file-option>] --unset name [value_regex]
'git config' [<file-option>] --unset-all name [value_regex]
'git config' [<file-option>] --rename-section old_name new_name
@@ -95,6 +96,14 @@ OPTIONS
in which section and variable names are lowercased, but subsection
names are not.
+--get-urlmatch name URL::
+ When given a two-part name section.key, the value for
+ section.<url>.key whose <url> part matches the best to the
+ given URL is returned (if no such key exists, the value for
+ section.key is used as a fallback). When given just the
+ section as name, do so for all the keys in the section and
+ list them.
+
--global::
For writing options: write to global `~/.gitconfig` file
rather than the repository `.git/config`, write to
@@ -295,6 +304,13 @@ Given a .git/config like this:
gitproxy=proxy-command for kernel.org
gitproxy=default-proxy ; for all the rest
+ ; HTTP
+ [http]
+ sslVerify
+ [http "https://weak.example.com"]
+ sslVerify = false
+ cookieFile = /tmp/cookie.txt
+
you can set the filemode to true with
------------
@@ -380,6 +396,19 @@ RESET=$(git config --get-color "" "reset")
echo "${WS}your whitespace color or blue reverse${RESET}"
------------
+For URLs in `https://weak.example.com`, `http.sslVerify` is set to
+false, while it is set to `true` for all others:
+
+------------
+% git config --bool --get-urlmatch http.sslverify https://good.example.com
+true
+% git config --bool --get-urlmatch http.sslverify https://weak.example.com
+false
+% git config --get-urlmatch http https://weak.example.com
+http.cookiefile /tmp/cookie.txt
+http.sslverify false
+------------
+
include::config.txt[]
GIT
diff --git a/Makefile b/Makefile
index 7051956333..9135cc9358 100644
--- a/Makefile
+++ b/Makefile
@@ -580,6 +580,7 @@ TEST_PROGRAMS_NEED_X += test-sigchain
TEST_PROGRAMS_NEED_X += test-string-list
TEST_PROGRAMS_NEED_X += test-subprocess
TEST_PROGRAMS_NEED_X += test-svn-fe
+TEST_PROGRAMS_NEED_X += test-urlmatch-normalization
TEST_PROGRAMS_NEED_X += test-wildmatch
TEST_PROGRAMS = $(patsubst %,%$X,$(TEST_PROGRAMS_NEED_X))
@@ -736,6 +737,7 @@ LIB_H += tree-walk.h
LIB_H += tree.h
LIB_H += unpack-trees.h
LIB_H += url.h
+LIB_H += urlmatch.h
LIB_H += userdiff.h
LIB_H += utf8.h
LIB_H += varint.h
@@ -886,6 +888,7 @@ LIB_OBJS += tree.o
LIB_OBJS += tree-walk.o
LIB_OBJS += unpack-trees.o
LIB_OBJS += url.o
+LIB_OBJS += urlmatch.o
LIB_OBJS += usage.o
LIB_OBJS += userdiff.o
LIB_OBJS += utf8.o
diff --git a/builtin/config.c b/builtin/config.c
index 4ab9e9a550..fc8d8820cb 100644
--- a/builtin/config.c
+++ b/builtin/config.c
@@ -2,6 +2,7 @@
#include "cache.h"
#include "color.h"
#include "parse-options.h"
+#include "urlmatch.h"
static const char *const builtin_config_usage[] = {
N_("git config [options]"),
@@ -42,6 +43,7 @@ static int respect_includes = -1;
#define ACTION_SET_ALL (1<<12)
#define ACTION_GET_COLOR (1<<13)
#define ACTION_GET_COLORBOOL (1<<14)
+#define ACTION_GET_URLMATCH (1<<15)
#define TYPE_BOOL (1<<0)
#define TYPE_INT (1<<1)
@@ -59,6 +61,7 @@ static struct option builtin_config_options[] = {
OPT_BIT(0, "get", &actions, N_("get value: name [value-regex]"), ACTION_GET),
OPT_BIT(0, "get-all", &actions, N_("get all values: key [value-regex]"), ACTION_GET_ALL),
OPT_BIT(0, "get-regexp", &actions, N_("get values for regexp: name-regex [value-regex]"), ACTION_GET_REGEXP),
+ OPT_BIT(0, "get-urlmatch", &actions, N_("get value specific for the URL: section[.var] URL"), ACTION_GET_URLMATCH),
OPT_BIT(0, "replace-all", &actions, N_("replace all matching variables: name value [value_regex]"), ACTION_REPLACE_ALL),
OPT_BIT(0, "add", &actions, N_("add a new variable: name value"), ACTION_ADD),
OPT_BIT(0, "unset", &actions, N_("remove a variable: name [value-regex]"), ACTION_UNSET),
@@ -102,25 +105,13 @@ struct strbuf_list {
int alloc;
};
-static int collect_config(const char *key_, const char *value_, void *cb)
+static int format_config(struct strbuf *buf, const char *key_, const char *value_)
{
- struct strbuf_list *values = cb;
- struct strbuf *buf;
- char value[256];
- const char *vptr = value;
int must_free_vptr = 0;
int must_print_delim = 0;
+ char value[256];
+ const char *vptr = value;
- if (!use_key_regexp && strcmp(key_, key))
- return 0;
- if (use_key_regexp && regexec(key_regexp, key_, 0, NULL, 0))
- return 0;
- if (regexp != NULL &&
- (do_not_match ^ !!regexec(regexp, (value_?value_:""), 0, NULL, 0)))
- return 0;
-
- ALLOC_GROW(values->items, values->nr + 1, values->alloc);
- buf = &values->items[values->nr++];
strbuf_init(buf, 0);
if (show_keys) {
@@ -128,7 +119,7 @@ static int collect_config(const char *key_, const char *value_, void *cb)
must_print_delim = 1;
}
if (types == TYPE_INT)
- sprintf(value, "%d", git_config_int(key_, value_?value_:""));
+ sprintf(value, "%d", git_config_int(key_, value_ ? value_ : ""));
else if (types == TYPE_BOOL)
vptr = git_config_bool(key_, value_) ? "true" : "false";
else if (types == TYPE_BOOL_OR_INT) {
@@ -156,15 +147,27 @@ static int collect_config(const char *key_, const char *value_, void *cb)
strbuf_addch(buf, term);
if (must_free_vptr)
- /* If vptr must be freed, it's a pointer to a
- * dynamically allocated buffer, it's safe to cast to
- * const.
- */
free((char *)vptr);
-
return 0;
}
+static int collect_config(const char *key_, const char *value_, void *cb)
+{
+ struct strbuf_list *values = cb;
+
+ if (!use_key_regexp && strcmp(key_, key))
+ return 0;
+ if (use_key_regexp && regexec(key_regexp, key_, 0, NULL, 0))
+ return 0;
+ if (regexp != NULL &&
+ (do_not_match ^ !!regexec(regexp, (value_?value_:""), 0, NULL, 0)))
+ return 0;
+
+ ALLOC_GROW(values->items, values->nr + 1, values->alloc);
+
+ return format_config(&values->items[values->nr++], key_, value_);
+}
+
static int get_value(const char *key_, const char *regex_)
{
int ret = CONFIG_GENERIC_ERROR;
@@ -364,6 +367,97 @@ static void check_blob_write(void)
die("writing config blobs is not supported");
}
+struct urlmatch_current_candidate_value {
+ char value_is_null;
+ struct strbuf value;
+};
+
+static int urlmatch_collect_fn(const char *var, const char *value, void *cb)
+{
+ struct string_list *values = cb;
+ struct string_list_item *item = string_list_insert(values, var);
+ struct urlmatch_current_candidate_value *matched = item->util;
+
+ if (!matched) {
+ matched = xmalloc(sizeof(*matched));
+ strbuf_init(&matched->value, 0);
+ item->util = matched;
+ } else {
+ strbuf_reset(&matched->value);
+ }
+
+ if (value) {
+ strbuf_addstr(&matched->value, value);
+ matched->value_is_null = 0;
+ } else {
+ matched->value_is_null = 1;
+ }
+ return 0;
+}
+
+static char *dup_downcase(const char *string)
+{
+ char *result;
+ size_t len, i;
+
+ len = strlen(string);
+ result = xmalloc(len + 1);
+ for (i = 0; i < len; i++)
+ result[i] = tolower(string[i]);
+ result[i] = '\0';
+ return result;
+}
+
+static int get_urlmatch(const char *var, const char *url)
+{
+ char *section_tail;
+ struct string_list_item *item;
+ struct urlmatch_config config = { STRING_LIST_INIT_DUP };
+ struct string_list values = STRING_LIST_INIT_DUP;
+
+ config.collect_fn = urlmatch_collect_fn;
+ config.cascade_fn = NULL;
+ config.cb = &values;
+
+ if (!url_normalize(url, &config.url))
+ die("%s", config.url.err);
+
+ config.section = dup_downcase(var);
+ section_tail = strchr(config.section, '.');
+ if (section_tail) {
+ *section_tail = '\0';
+ config.key = section_tail + 1;
+ show_keys = 0;
+ } else {
+ config.key = NULL;
+ show_keys = 1;
+ }
+
+ git_config_with_options(urlmatch_config_entry, &config,
+ given_config_file, NULL, respect_includes);
+
+ for_each_string_list_item(item, &values) {
+ struct urlmatch_current_candidate_value *matched = item->util;
+ struct strbuf key = STRBUF_INIT;
+ struct strbuf buf = STRBUF_INIT;
+
+ strbuf_addstr(&key, item->string);
+ format_config(&buf, key.buf,
+ matched->value_is_null ? NULL : matched->value.buf);
+ fwrite(buf.buf, 1, buf.len, stdout);
+ strbuf_release(&key);
+ strbuf_release(&buf);
+
+ strbuf_release(&matched->value);
+ }
+ string_list_clear(&config.vars, 1);
+ string_list_clear(&values, 1);
+ free(config.url.url);
+
+ free((void *)config.section);
+ return 0;
+}
+
int cmd_config(int argc, const char **argv, const char *prefix)
{
int nongit = !startup_info->have_repository;
@@ -523,6 +617,10 @@ int cmd_config(int argc, const char **argv, const char *prefix)
check_argc(argc, 1, 2);
return get_value(argv[0], argv[1]);
}
+ else if (actions == ACTION_GET_URLMATCH) {
+ check_argc(argc, 2, 2);
+ return get_urlmatch(argv[0], argv[1]);
+ }
else if (actions == ACTION_UNSET) {
check_blob_write();
check_argc(argc, 1, 2);
diff --git a/http.c b/http.c
index 2fbf986231..f3e1439d58 100644
--- a/http.c
+++ b/http.c
@@ -3,6 +3,7 @@
#include "sideband.h"
#include "run-command.h"
#include "url.h"
+#include "urlmatch.h"
#include "credential.h"
#include "version.h"
#include "pkt-line.h"
@@ -161,8 +162,7 @@ static int http_options(const char *var, const char *value, void *cb)
if (!strcmp("http.sslcainfo", var))
return git_config_string(&ssl_cainfo, var, value);
if (!strcmp("http.sslcertpasswordprotected", var)) {
- if (git_config_bool(var, value))
- ssl_cert_password_required = 1;
+ ssl_cert_password_required = git_config_bool(var, value);
return 0;
}
if (!strcmp("http.ssltry", var)) {
@@ -346,10 +346,20 @@ void http_init(struct remote *remote, const char *url, int proactive_auth)
{
char *low_speed_limit;
char *low_speed_time;
+ char *normalized_url;
+ struct urlmatch_config config = { STRING_LIST_INIT_DUP };
+
+ config.section = "http";
+ config.key = NULL;
+ config.collect_fn = http_options;
+ config.cascade_fn = git_default_config;
+ config.cb = NULL;
http_is_verbose = 0;
+ normalized_url = url_normalize(url, &config.url);
- git_config(http_options, NULL);
+ git_config(urlmatch_config_entry, &config);
+ free(normalized_url);
curl_global_init(CURL_GLOBAL_ALL);
diff --git a/t/.gitattributes b/t/.gitattributes
index 1b97c5465b..2d44088f56 100644
--- a/t/.gitattributes
+++ b/t/.gitattributes
@@ -1 +1,2 @@
t[0-9][0-9][0-9][0-9]/* -whitespace
+t0110/url-* binary
diff --git a/t/t0110-urlmatch-normalization.sh b/t/t0110-urlmatch-normalization.sh
new file mode 100755
index 0000000000..8d6096d4d1
--- /dev/null
+++ b/t/t0110-urlmatch-normalization.sh
@@ -0,0 +1,177 @@
+#!/bin/sh
+
+test_description='urlmatch URL normalization'
+. ./test-lib.sh
+
+# The base name of the test url files
+tu="$TEST_DIRECTORY/t0110/url"
+
+# Note that only file: URLs should be allowed without a host
+
+test_expect_success 'url scheme' '
+ ! test-urlmatch-normalization "" &&
+ ! test-urlmatch-normalization "_" &&
+ ! test-urlmatch-normalization "scheme" &&
+ ! test-urlmatch-normalization "scheme:" &&
+ ! test-urlmatch-normalization "scheme:/" &&
+ ! test-urlmatch-normalization "scheme://" &&
+ ! test-urlmatch-normalization "file" &&
+ ! test-urlmatch-normalization "file:" &&
+ ! test-urlmatch-normalization "file:/" &&
+ test-urlmatch-normalization "file://" &&
+ ! test-urlmatch-normalization "://acme.co" &&
+ ! test-urlmatch-normalization "x_test://acme.co" &&
+ ! test-urlmatch-normalization "-test://acme.co" &&
+ ! test-urlmatch-normalization "0test://acme.co" &&
+ ! test-urlmatch-normalization "+test://acme.co" &&
+ ! test-urlmatch-normalization ".test://acme.co" &&
+ ! test-urlmatch-normalization "schem%6e://" &&
+ test-urlmatch-normalization "x-Test+v1.0://acme.co" &&
+ test "$(test-urlmatch-normalization -p "AbCdeF://x.Y")" = "abcdef://x.y/"
+'
+
+test_expect_success 'url authority' '
+ ! test-urlmatch-normalization "scheme://user:pass@" &&
+ ! test-urlmatch-normalization "scheme://?" &&
+ ! test-urlmatch-normalization "scheme://#" &&
+ ! test-urlmatch-normalization "scheme:///" &&
+ ! test-urlmatch-normalization "scheme://:" &&
+ ! test-urlmatch-normalization "scheme://:555" &&
+ test-urlmatch-normalization "file://user:pass@" &&
+ test-urlmatch-normalization "file://?" &&
+ test-urlmatch-normalization "file://#" &&
+ test-urlmatch-normalization "file:///" &&
+ test-urlmatch-normalization "file://:" &&
+ ! test-urlmatch-normalization "file://:555" &&
+ test-urlmatch-normalization "scheme://user:pass@host" &&
+ test-urlmatch-normalization "scheme://@host" &&
+ test-urlmatch-normalization "scheme://%00@host" &&
+ ! test-urlmatch-normalization "scheme://%%@host" &&
+ ! test-urlmatch-normalization "scheme://host_" &&
+ test-urlmatch-normalization "scheme://user:pass@host/" &&
+ test-urlmatch-normalization "scheme://@host/" &&
+ test-urlmatch-normalization "scheme://host/" &&
+ test-urlmatch-normalization "scheme://host?x" &&
+ test-urlmatch-normalization "scheme://host#x" &&
+ test-urlmatch-normalization "scheme://host/@" &&
+ test-urlmatch-normalization "scheme://host?@x" &&
+ test-urlmatch-normalization "scheme://host#@x" &&
+ test-urlmatch-normalization "scheme://[::1]" &&
+ test-urlmatch-normalization "scheme://[::1]/" &&
+ ! test-urlmatch-normalization "scheme://hos%41/" &&
+ test-urlmatch-normalization "scheme://[invalid....:/" &&
+ test-urlmatch-normalization "scheme://invalid....:]/" &&
+ ! test-urlmatch-normalization "scheme://invalid....:[/" &&
+ ! test-urlmatch-normalization "scheme://invalid....:["
+'
+
+test_expect_success 'url port checks' '
+ test-urlmatch-normalization "xyz://q@some.host:" &&
+ test-urlmatch-normalization "xyz://q@some.host:456/" &&
+ ! test-urlmatch-normalization "xyz://q@some.host:0" &&
+ ! test-urlmatch-normalization "xyz://q@some.host:0000000" &&
+ test-urlmatch-normalization "xyz://q@some.host:0000001?" &&
+ test-urlmatch-normalization "xyz://q@some.host:065535#" &&
+ test-urlmatch-normalization "xyz://q@some.host:65535" &&
+ ! test-urlmatch-normalization "xyz://q@some.host:65536" &&
+ ! test-urlmatch-normalization "xyz://q@some.host:99999" &&
+ ! test-urlmatch-normalization "xyz://q@some.host:100000" &&
+ ! test-urlmatch-normalization "xyz://q@some.host:100001" &&
+ test-urlmatch-normalization "http://q@some.host:80" &&
+ test-urlmatch-normalization "https://q@some.host:443" &&
+ test-urlmatch-normalization "http://q@some.host:80/" &&
+ test-urlmatch-normalization "https://q@some.host:443?" &&
+ ! test-urlmatch-normalization "http://q@:8008" &&
+ ! test-urlmatch-normalization "http://:8080" &&
+ ! test-urlmatch-normalization "http://:" &&
+ test-urlmatch-normalization "xyz://q@some.host:456/" &&
+ test-urlmatch-normalization "xyz://[::1]:456/" &&
+ test-urlmatch-normalization "xyz://[::1]:/" &&
+ ! test-urlmatch-normalization "xyz://[::1]:000/" &&
+ ! test-urlmatch-normalization "xyz://[::1]:0%300/" &&
+ ! test-urlmatch-normalization "xyz://[::1]:0x80/" &&
+ ! test-urlmatch-normalization "xyz://[::1]:4294967297/" &&
+ ! test-urlmatch-normalization "xyz://[::1]:030f/"
+'
+
+test_expect_success 'url port normalization' '
+ test "$(test-urlmatch-normalization -p "http://x:800")" = "http://x:800/" &&
+ test "$(test-urlmatch-normalization -p "http://x:0800")" = "http://x:800/" &&
+ test "$(test-urlmatch-normalization -p "http://x:00000800")" = "http://x:800/" &&
+ test "$(test-urlmatch-normalization -p "http://x:065535")" = "http://x:65535/" &&
+ test "$(test-urlmatch-normalization -p "http://x:1")" = "http://x:1/" &&
+ test "$(test-urlmatch-normalization -p "http://x:80")" = "http://x/" &&
+ test "$(test-urlmatch-normalization -p "http://x:080")" = "http://x/" &&
+ test "$(test-urlmatch-normalization -p "http://x:000000080")" = "http://x/" &&
+ test "$(test-urlmatch-normalization -p "https://x:443")" = "https://x/" &&
+ test "$(test-urlmatch-normalization -p "https://x:0443")" = "https://x/" &&
+ test "$(test-urlmatch-normalization -p "https://x:000000443")" = "https://x/"
+'
+
+test_expect_success 'url general escapes' '
+ ! test-urlmatch-normalization "http://x.y?%fg" &&
+ test "$(test-urlmatch-normalization -p "X://W/%7e%41^%3a")" = "x://w/~A%5E%3A" &&
+ test "$(test-urlmatch-normalization -p "X://W/:/?#[]@")" = "x://w/:/?#[]@" &&
+ test "$(test-urlmatch-normalization -p "X://W/$&()*+,;=")" = "x://w/$&()*+,;=" &&
+ test "$(test-urlmatch-normalization -p "X://W/'\''")" = "x://w/'\''" &&
+ test "$(test-urlmatch-normalization -p "X://W?'\!'")" = "x://w/?'\!'"
+'
+
+test_expect_success 'url high-bit escapes' '
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-1")")" = "x://q/%01%02%03%04%05%06%07%08%0E%0F%10%11%12" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-2")")" = "x://q/%13%14%15%16%17%18%19%1B%1C%1D%1E%1F%7F" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-3")")" = "x://q/%80%81%82%83%84%85%86%87%88%89%8A%8B%8C%8D%8E%8F" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-4")")" = "x://q/%90%91%92%93%94%95%96%97%98%99%9A%9B%9C%9D%9E%9F" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-5")")" = "x://q/%A0%A1%A2%A3%A4%A5%A6%A7%A8%A9%AA%AB%AC%AD%AE%AF" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-6")")" = "x://q/%B0%B1%B2%B3%B4%B5%B6%B7%B8%B9%BA%BB%BC%BD%BE%BF" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-7")")" = "x://q/%C0%C1%C2%C3%C4%C5%C6%C7%C8%C9%CA%CB%CC%CD%CE%CF" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-8")")" = "x://q/%D0%D1%D2%D3%D4%D5%D6%D7%D8%D9%DA%DB%DC%DD%DE%DF" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-9")")" = "x://q/%E0%E1%E2%E3%E4%E5%E6%E7%E8%E9%EA%EB%EC%ED%EE%EF" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-10")")" = "x://q/%F0%F1%F2%F3%F4%F5%F6%F7%F8%F9%FA%FB%FC%FD%FE%FF" &&
+ test "$(test-urlmatch-normalization -p "$(cat "$tu-11")")" = "x://q/%C2%80%DF%BF%E0%A0%80%EF%BF%BD%F0%90%80%80%F0%AF%BF%BD"
+'
+
+test_expect_success 'url username/password escapes' '
+ test "$(test-urlmatch-normalization -p "x://%41%62(^):%70+d@foo")" = "x://Ab(%5E):p+d@foo/"
+'
+
+test_expect_success 'url normalized lengths' '
+ test "$(test-urlmatch-normalization -l "Http://%4d%65:%4d^%70@The.Host")" = 25 &&
+ test "$(test-urlmatch-normalization -l "http://%41:%42@x.y/%61/")" = 17 &&
+ test "$(test-urlmatch-normalization -l "http://@x.y/^")" = 15
+'
+
+test_expect_success 'url . and .. segments' '
+ test "$(test-urlmatch-normalization -p "x://y/.")" = "x://y/" &&
+ test "$(test-urlmatch-normalization -p "x://y/./")" = "x://y/" &&
+ test "$(test-urlmatch-normalization -p "x://y/a/.")" = "x://y/a" &&
+ test "$(test-urlmatch-normalization -p "x://y/a/./")" = "x://y/a/" &&
+ test "$(test-urlmatch-normalization -p "x://y/.?")" = "x://y/?" &&
+ test "$(test-urlmatch-normalization -p "x://y/./?")" = "x://y/?" &&
+ test "$(test-urlmatch-normalization -p "x://y/a/.?")" = "x://y/a?" &&
+ test "$(test-urlmatch-normalization -p "x://y/a/./?")" = "x://y/a/?" &&
+ test "$(test-urlmatch-normalization -p "x://y/a/./b/.././../c")" = "x://y/c" &&
+ test "$(test-urlmatch-normalization -p "x://y/a/./b/../.././c/")" = "x://y/c/" &&
+ test "$(test-urlmatch-normalization -p "x://y/a/./b/.././../c/././.././.")" = "x://y/" &&
+ ! test-urlmatch-normalization "x://y/a/./b/.././../c/././.././.." &&
+ test "$(test-urlmatch-normalization -p "x://y/a/./?/././..")" = "x://y/a/?/././.." &&
+ test "$(test-urlmatch-normalization -p "x://y/%2e/")" = "x://y/" &&
+ test "$(test-urlmatch-normalization -p "x://y/%2E/")" = "x://y/" &&
+ test "$(test-urlmatch-normalization -p "x://y/a/%2e./")" = "x://y/" &&
+ test "$(test-urlmatch-normalization -p "x://y/b/.%2E/")" = "x://y/" &&
+ test "$(test-urlmatch-normalization -p "x://y/c/%2e%2E/")" = "x://y/"
+'
+
+# http://@foo specifies an empty user name but does not specify a password
+# http://foo specifies neither a user name nor a password
+# So they should not be equivalent
+test_expect_success 'url equivalents' '
+ test-urlmatch-normalization "httP://x" "Http://X/" &&
+ test-urlmatch-normalization "Http://%4d%65:%4d^%70@The.Host" "hTTP://Me:%4D^p@the.HOST:80/" &&
+ ! test-urlmatch-normalization "https://@x.y/^" "httpS://x.y:443/^" &&
+ test-urlmatch-normalization "https://@x.y/^" "httpS://@x.y:0443/^" &&
+ test-urlmatch-normalization "https://@x.y/^/../abc" "httpS://@x.y:0443/abc" &&
+ test-urlmatch-normalization "https://@x.y/^/.." "httpS://@x.y:0443/"
+'
+
+test_done
diff --git a/t/t0110/README b/t/t0110/README
new file mode 100644
index 0000000000..ad4a50ecd8
--- /dev/null
+++ b/t/t0110/README
@@ -0,0 +1,9 @@
+The url data files in this directory contain URLs with characters
+in the range 0x01-0x1f and 0x7f-0xff to test the proper normalization
+of unprintable characters.
+
+A select few characters in the 0x01-0x1f range are skipped to help
+avoid problems running the test itself.
+
+The urls are in test files in this directory rather than being
+embedded in the test script for portability.
diff --git a/t/t0110/url-1 b/t/t0110/url-1
new file mode 100644
index 0000000000..519019c5ce
--- /dev/null
+++ b/t/t0110/url-1
@@ -0,0 +1 @@
+x://q/
diff --git a/t/t0110/url-10 b/t/t0110/url-10
new file mode 100644
index 0000000000..b9965de6a5
--- /dev/null
+++ b/t/t0110/url-10
@@ -0,0 +1 @@
+x://q/ðñòóôõö÷øùúûüýþÿ
diff --git a/t/t0110/url-11 b/t/t0110/url-11
new file mode 100644
index 0000000000..f0a50f1009
--- /dev/null
+++ b/t/t0110/url-11
@@ -0,0 +1 @@
+x://q/€߿ࠀ�ð€€ð¯¿½
diff --git a/t/t0110/url-2 b/t/t0110/url-2
new file mode 100644
index 0000000000..43334b05b2
--- /dev/null
+++ b/t/t0110/url-2
@@ -0,0 +1 @@
+x://q/
diff --git a/t/t0110/url-3 b/t/t0110/url-3
new file mode 100644
index 0000000000..7378c7bec2
--- /dev/null
+++ b/t/t0110/url-3
@@ -0,0 +1 @@
+x://q/€‚ƒ„…†‡ˆ‰Š‹ŒŽ
diff --git a/t/t0110/url-4 b/t/t0110/url-4
new file mode 100644
index 0000000000..220b198c97
--- /dev/null
+++ b/t/t0110/url-4
@@ -0,0 +1 @@
+x://q/‘’“”•–—˜™š›œžŸ
diff --git a/t/t0110/url-5 b/t/t0110/url-5
new file mode 100644
index 0000000000..1ccd927779
--- /dev/null
+++ b/t/t0110/url-5
@@ -0,0 +1 @@
+x://q/ ¡¢£¤¥¦§¨©ª«¬­®¯
diff --git a/t/t0110/url-6 b/t/t0110/url-6
new file mode 100644
index 0000000000..e8283aac6d
--- /dev/null
+++ b/t/t0110/url-6
@@ -0,0 +1 @@
+x://q/°±²³´µ¶·¸¹º»¼½¾¿
diff --git a/t/t0110/url-7 b/t/t0110/url-7
new file mode 100644
index 0000000000..fa7c10b615
--- /dev/null
+++ b/t/t0110/url-7
@@ -0,0 +1 @@
+x://q/ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ
diff --git a/t/t0110/url-8 b/t/t0110/url-8
new file mode 100644
index 0000000000..79a0ba836f
--- /dev/null
+++ b/t/t0110/url-8
@@ -0,0 +1 @@
+x://q/ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞß
diff --git a/t/t0110/url-9 b/t/t0110/url-9
new file mode 100644
index 0000000000..8b44bec48b
--- /dev/null
+++ b/t/t0110/url-9
@@ -0,0 +1 @@
+x://q/àáâãäåæçèéêëìíîï
diff --git a/t/t1300-repo-config.sh b/t/t1300-repo-config.sh
index c4a7d84f46..c23f4781e1 100755
--- a/t/t1300-repo-config.sh
+++ b/t/t1300-repo-config.sh
@@ -1087,6 +1087,31 @@ test_expect_success 'barf on incomplete string' '
grep " line 3 " error
'
+test_expect_success 'urlmatch' '
+ cat >.git/config <<-\EOF &&
+ [http]
+ sslVerify
+ [http "https://weak.example.com"]
+ sslVerify = false
+ cookieFile = /tmp/cookie.txt
+ EOF
+
+ echo true >expect &&
+ git config --bool --get-urlmatch http.SSLverify https://good.example.com >actual &&
+ test_cmp expect actual &&
+
+ echo false >expect &&
+ git config --bool --get-urlmatch http.sslverify https://weak.example.com >actual &&
+ test_cmp expect actual &&
+
+ {
+ echo http.cookiefile /tmp/cookie.txt &&
+ echo http.sslverify false
+ } >expect &&
+ git config --get-urlmatch HTTP https://weak.example.com >actual &&
+ test_cmp expect actual
+'
+
# good section hygiene
test_expect_failure 'unsetting the last key in a section removes header' '
cat >.git/config <<-\EOF &&
diff --git a/test-urlmatch-normalization.c b/test-urlmatch-normalization.c
new file mode 100644
index 0000000000..090bf219a7
--- /dev/null
+++ b/test-urlmatch-normalization.c
@@ -0,0 +1,50 @@
+#include "git-compat-util.h"
+#include "urlmatch.h"
+
+int main(int argc, char **argv)
+{
+ const char usage[] = "test-urlmatch-normalization [-p | -l] <url1> | <url1> <url2>";
+ char *url1, *url2;
+ int opt_p = 0, opt_l = 0;
+
+ /*
+ * For one url, succeed if url_normalize succeeds on it, fail otherwise.
+ * For two urls, succeed only if url_normalize succeeds on both and
+ * the results compare equal with strcmp. If -p is given (one url only)
+ * and url_normalize succeeds, print the result followed by "\n". If
+ * -l is given (one url only) and url_normalize succeeds, print the
+ * returned length in decimal followed by "\n".
+ */
+
+ if (argc > 1 && !strcmp(argv[1], "-p")) {
+ opt_p = 1;
+ argc--;
+ argv++;
+ } else if (argc > 1 && !strcmp(argv[1], "-l")) {
+ opt_l = 1;
+ argc--;
+ argv++;
+ }
+
+ if (argc < 2 || argc > 3)
+ die("%s", usage);
+
+ if (argc == 2) {
+ struct url_info info;
+ url1 = url_normalize(argv[1], &info);
+ if (!url1)
+ return 1;
+ if (opt_p)
+ printf("%s\n", url1);
+ if (opt_l)
+ printf("%u\n", (unsigned)info.url_len);
+ return 0;
+ }
+
+ if (opt_p || opt_l)
+ die("%s", usage);
+
+ url1 = url_normalize(argv[1], NULL);
+ url2 = url_normalize(argv[2], NULL);
+ return (url1 && url2 && !strcmp(url1, url2)) ? 0 : 1;
+}
diff --git a/urlmatch.c b/urlmatch.c
new file mode 100644
index 0000000000..1db76c89bc
--- /dev/null
+++ b/urlmatch.c
@@ -0,0 +1,535 @@
+#include "cache.h"
+#include "urlmatch.h"
+
+#define URL_ALPHA "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
+#define URL_DIGIT "0123456789"
+#define URL_ALPHADIGIT URL_ALPHA URL_DIGIT
+#define URL_SCHEME_CHARS URL_ALPHADIGIT "+.-"
+#define URL_HOST_CHARS URL_ALPHADIGIT ".-[:]" /* IPv6 literals need [:] */
+#define URL_UNSAFE_CHARS " <>\"%{}|\\^`" /* plus 0x00-0x1F,0x7F-0xFF */
+#define URL_GEN_RESERVED ":/?#[]@"
+#define URL_SUB_RESERVED "!$&'()*+,;="
+#define URL_RESERVED URL_GEN_RESERVED URL_SUB_RESERVED /* only allowed delims */
+
+static int append_normalized_escapes(struct strbuf *buf,
+ const char *from,
+ size_t from_len,
+ const char *esc_extra,
+ const char *esc_ok)
+{
+ /*
+ * Append to strbuf 'buf' characters from string 'from' with length
+ * 'from_len' while unescaping characters that do not need to be escaped
+ * and escaping characters that do. The set of characters to escape
+ * (the complement of which is unescaped) starts out as the RFC 3986
+ * unsafe characters (0x00-0x1F,0x7F-0xFF," <>\"#%{}|\\^`"). If
+ * 'esc_extra' is not NULL, those additional characters will also always
+ * be escaped. If 'esc_ok' is not NULL, those characters will be left
+ * escaped if found that way, but will not be unescaped otherwise (used
+ * for delimiters). If a %-escape sequence is encountered that is not
+ * followed by 2 hexadecimal digits, the sequence is invalid and
+ * false (0) will be returned. Otherwise true (1) will be returned for
+ * success.
+ *
+ * Note that all %-escape sequences will be normalized to UPPERCASE
+ * as indicated in RFC 3986. Unless included in esc_extra or esc_ok
+ * alphanumerics and "-._~" will always be unescaped as per RFC 3986.
+ */
+
+ while (from_len) {
+ int ch = *from++;
+ int was_esc = 0;
+
+ from_len--;
+ if (ch == '%') {
+ if (from_len < 2 ||
+ !isxdigit((unsigned char)from[0]) ||
+ !isxdigit((unsigned char)from[1]))
+ return 0;
+ ch = hexval_table[(unsigned char)*from++] << 4;
+ ch |= hexval_table[(unsigned char)*from++];
+ from_len -= 2;
+ was_esc = 1;
+ }
+ if ((unsigned char)ch <= 0x1F || (unsigned char)ch >= 0x7F ||
+ strchr(URL_UNSAFE_CHARS, ch) ||
+ (esc_extra && strchr(esc_extra, ch)) ||
+ (was_esc && strchr(esc_ok, ch)))
+ strbuf_addf(buf, "%%%02X", (unsigned char)ch);
+ else
+ strbuf_addch(buf, ch);
+ }
+
+ return 1;
+}
+
+char *url_normalize(const char *url, struct url_info *out_info)
+{
+ /*
+ * Normalize NUL-terminated url using the following rules:
+ *
+ * 1. Case-insensitive parts of url will be converted to lower case
+ * 2. %-encoded characters that do not need to be will be unencoded
+ * 3. Characters that are not %-encoded and must be will be encoded
+ * 4. All %-encodings will be converted to upper case hexadecimal
+ * 5. Leading 0s are removed from port numbers
+ * 6. If the default port for the scheme is given it will be removed
+ * 7. A path part (including empty) not starting with '/' has one added
+ * 8. Any dot segments (. or ..) in the path are resolved and removed
+ * 9. IPv6 host literals are allowed (but not normalized or validated)
+ *
+ * The rules are based on information in RFC 3986.
+ *
+ * Please note this function requires a full URL including a scheme
+ * and host part (except for file: URLs which may have an empty host).
+ *
+ * The return value is a newly allocated string that must be freed
+ * or NULL if the url is not valid.
+ *
+ * If out_info is non-NULL, the url and err fields therein will always
+ * be set. If a non-NULL value is returned, it will be stored in
+ * out_info->url as well, out_info->err will be set to NULL and the
+ * other fields of *out_info will also be filled in. If a NULL value
+ * is returned, NULL will be stored in out_info->url and out_info->err
+ * will be set to a brief, translated, error message, but no other
+ * fields will be filled in.
+ *
+ * This is NOT a URL validation function. Full URL validation is NOT
+ * performed. Some invalid host names are passed through this function
+ * undetected. However, most all other problems that make a URL invalid
+ * will be detected (including a missing host for non file: URLs).
+ */
+
+ size_t url_len = strlen(url);
+ struct strbuf norm;
+ size_t spanned;
+ size_t scheme_len, user_off=0, user_len=0, passwd_off=0, passwd_len=0;
+ size_t host_off=0, host_len=0, port_len=0, path_off, path_len, result_len;
+ const char *slash_ptr, *at_ptr, *colon_ptr, *path_start;
+ char *result;
+
+ /*
+ * Copy lowercased scheme and :// suffix, %-escapes are not allowed
+ * First character of scheme must be URL_ALPHA
+ */
+ spanned = strspn(url, URL_SCHEME_CHARS);
+ if (!spanned || !isalpha(url[0]) || spanned + 3 > url_len ||
+ url[spanned] != ':' || url[spanned+1] != '/' || url[spanned+2] != '/') {
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("invalid URL scheme name or missing '://' suffix");
+ }
+ return NULL; /* Bad scheme and/or missing "://" part */
+ }
+ strbuf_init(&norm, url_len);
+ scheme_len = spanned;
+ spanned += 3;
+ url_len -= spanned;
+ while (spanned--)
+ strbuf_addch(&norm, tolower(*url++));
+
+
+ /*
+ * Copy any username:password if present normalizing %-escapes
+ */
+ at_ptr = strchr(url, '@');
+ slash_ptr = url + strcspn(url, "/?#");
+ if (at_ptr && at_ptr < slash_ptr) {
+ user_off = norm.len;
+ if (at_ptr > url) {
+ if (!append_normalized_escapes(&norm, url, at_ptr - url,
+ "", URL_RESERVED)) {
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("invalid %XX escape sequence");
+ }
+ strbuf_release(&norm);
+ return NULL;
+ }
+ colon_ptr = strchr(norm.buf + scheme_len + 3, ':');
+ if (colon_ptr) {
+ passwd_off = (colon_ptr + 1) - norm.buf;
+ passwd_len = norm.len - passwd_off;
+ user_len = (passwd_off - 1) - (scheme_len + 3);
+ } else {
+ user_len = norm.len - (scheme_len + 3);
+ }
+ }
+ strbuf_addch(&norm, '@');
+ url_len -= (++at_ptr - url);
+ url = at_ptr;
+ }
+
+
+ /*
+ * Copy the host part excluding any port part, no %-escapes allowed
+ */
+ if (!url_len || strchr(":/?#", *url)) {
+ /* Missing host invalid for all URL schemes except file */
+ if (strncmp(norm.buf, "file:", 5)) {
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("missing host and scheme is not 'file:'");
+ }
+ strbuf_release(&norm);
+ return NULL;
+ }
+ } else {
+ host_off = norm.len;
+ }
+ colon_ptr = slash_ptr - 1;
+ while (colon_ptr > url && *colon_ptr != ':' && *colon_ptr != ']')
+ colon_ptr--;
+ if (*colon_ptr != ':') {
+ colon_ptr = slash_ptr;
+ } else if (!host_off && colon_ptr < slash_ptr && colon_ptr + 1 != slash_ptr) {
+ /* file: URLs may not have a port number */
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("a 'file:' URL may not have a port number");
+ }
+ strbuf_release(&norm);
+ return NULL;
+ }
+ spanned = strspn(url, URL_HOST_CHARS);
+ if (spanned < colon_ptr - url) {
+ /* Host name has invalid characters */
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("invalid characters in host name");
+ }
+ strbuf_release(&norm);
+ return NULL;
+ }
+ while (url < colon_ptr) {
+ strbuf_addch(&norm, tolower(*url++));
+ url_len--;
+ }
+
+
+ /*
+ * Check the port part and copy if not the default (after removing any
+ * leading 0s); no %-escapes allowed
+ */
+ if (colon_ptr < slash_ptr) {
+ /* skip the ':' and leading 0s but not the last one if all 0s */
+ url++;
+ url += strspn(url, "0");
+ if (url == slash_ptr && url[-1] == '0')
+ url--;
+ if (url == slash_ptr) {
+ /* Skip ":" port with no number, it's same as default */
+ } else if (slash_ptr - url == 2 &&
+ !strncmp(norm.buf, "http:", 5) &&
+ !strncmp(url, "80", 2)) {
+ /* Skip http :80 as it's the default */
+ } else if (slash_ptr - url == 3 &&
+ !strncmp(norm.buf, "https:", 6) &&
+ !strncmp(url, "443", 3)) {
+ /* Skip https :443 as it's the default */
+ } else {
+ /*
+ * Port number must be all digits with leading 0s removed
+ * and since all the protocols we deal with have a 16-bit
+ * port number it must also be in the range 1..65535
+ * 0 is not allowed because that means "next available"
+ * on just about every system and therefore cannot be used
+ */
+ unsigned long pnum = 0;
+ spanned = strspn(url, URL_DIGIT);
+ if (spanned < slash_ptr - url) {
+ /* port number has invalid characters */
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("invalid port number");
+ }
+ strbuf_release(&norm);
+ return NULL;
+ }
+ if (slash_ptr - url <= 5)
+ pnum = strtoul(url, NULL, 10);
+ if (pnum == 0 || pnum > 65535) {
+ /* port number not in range 1..65535 */
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("invalid port number");
+ }
+ strbuf_release(&norm);
+ return NULL;
+ }
+ strbuf_addch(&norm, ':');
+ strbuf_add(&norm, url, slash_ptr - url);
+ port_len = slash_ptr - url;
+ }
+ url_len -= slash_ptr - colon_ptr;
+ url = slash_ptr;
+ }
+ if (host_off)
+ host_len = norm.len - host_off;
+
+
+ /*
+ * Now copy the path resolving any . and .. segments being careful not
+ * to corrupt the URL by unescaping any delimiters, but do add an
+ * initial '/' if it's missing and do normalize any %-escape sequences.
+ */
+ path_off = norm.len;
+ path_start = norm.buf + path_off;
+ strbuf_addch(&norm, '/');
+ if (*url == '/') {
+ url++;
+ url_len--;
+ }
+ for (;;) {
+ const char *seg_start = norm.buf + norm.len;
+ const char *next_slash = url + strcspn(url, "/?#");
+ int skip_add_slash = 0;
+ /*
+ * RFC 3689 indicates that any . or .. segments should be
+ * unescaped before being checked for.
+ */
+ if (!append_normalized_escapes(&norm, url, next_slash - url, "",
+ URL_RESERVED)) {
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("invalid %XX escape sequence");
+ }
+ strbuf_release(&norm);
+ return NULL;
+ }
+ if (!strcmp(seg_start, ".")) {
+ /* ignore a . segment; be careful not to remove initial '/' */
+ if (seg_start == path_start + 1) {
+ strbuf_setlen(&norm, norm.len - 1);
+ skip_add_slash = 1;
+ } else {
+ strbuf_setlen(&norm, norm.len - 2);
+ }
+ } else if (!strcmp(seg_start, "..")) {
+ /*
+ * ignore a .. segment and remove the previous segment;
+ * be careful not to remove initial '/' from path
+ */
+ const char *prev_slash = norm.buf + norm.len - 3;
+ if (prev_slash == path_start) {
+ /* invalid .. because no previous segment to remove */
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("invalid '..' path segment");
+ }
+ strbuf_release(&norm);
+ return NULL;
+ }
+ while (*--prev_slash != '/') {}
+ if (prev_slash == path_start) {
+ strbuf_setlen(&norm, prev_slash - norm.buf + 1);
+ skip_add_slash = 1;
+ } else {
+ strbuf_setlen(&norm, prev_slash - norm.buf);
+ }
+ }
+ url_len -= next_slash - url;
+ url = next_slash;
+ /* if the next char is not '/' done with the path */
+ if (*url != '/')
+ break;
+ url++;
+ url_len--;
+ if (!skip_add_slash)
+ strbuf_addch(&norm, '/');
+ }
+ path_len = norm.len - path_off;
+
+
+ /*
+ * Now simply copy the rest, if any, only normalizing %-escapes and
+ * being careful not to corrupt the URL by unescaping any delimiters.
+ */
+ if (*url) {
+ if (!append_normalized_escapes(&norm, url, url_len, "", URL_RESERVED)) {
+ if (out_info) {
+ out_info->url = NULL;
+ out_info->err = _("invalid %XX escape sequence");
+ }
+ strbuf_release(&norm);
+ return NULL;
+ }
+ }
+
+
+ result = strbuf_detach(&norm, &result_len);
+ if (out_info) {
+ out_info->url = result;
+ out_info->err = NULL;
+ out_info->url_len = result_len;
+ out_info->scheme_len = scheme_len;
+ out_info->user_off = user_off;
+ out_info->user_len = user_len;
+ out_info->passwd_off = passwd_off;
+ out_info->passwd_len = passwd_len;
+ out_info->host_off = host_off;
+ out_info->host_len = host_len;
+ out_info->port_len = port_len;
+ out_info->path_off = path_off;
+ out_info->path_len = path_len;
+ }
+ return result;
+}
+
+static size_t url_match_prefix(const char *url,
+ const char *url_prefix,
+ size_t url_prefix_len)
+{
+ /*
+ * url_prefix matches url if url_prefix is an exact match for url or it
+ * is a prefix of url and the match ends on a path component boundary.
+ * Both url and url_prefix are considered to have an implicit '/' on the
+ * end for matching purposes if they do not already.
+ *
+ * url must be NUL terminated. url_prefix_len is the length of
+ * url_prefix which need not be NUL terminated.
+ *
+ * The return value is the length of the match in characters (including
+ * the final '/' even if it's implicit) or 0 for no match.
+ *
+ * Passing NULL as url and/or url_prefix will always cause 0 to be
+ * returned without causing any faults.
+ */
+ if (!url || !url_prefix)
+ return 0;
+ if (!url_prefix_len || (url_prefix_len == 1 && *url_prefix == '/'))
+ return (!*url || *url == '/') ? 1 : 0;
+ if (url_prefix[url_prefix_len - 1] == '/')
+ url_prefix_len--;
+ if (strncmp(url, url_prefix, url_prefix_len))
+ return 0;
+ if ((strlen(url) == url_prefix_len) || (url[url_prefix_len] == '/'))
+ return url_prefix_len + 1;
+ return 0;
+}
+
+int match_urls(const struct url_info *url,
+ const struct url_info *url_prefix,
+ int *exactusermatch)
+{
+ /*
+ * url_prefix matches url if the scheme, host and port of url_prefix
+ * are the same as those of url and the path portion of url_prefix
+ * is the same as the path portion of url or it is a prefix that
+ * matches at a '/' boundary. If url_prefix contains a user name,
+ * that must also exactly match the user name in url.
+ *
+ * If the user, host, port and path match in this fashion, the returned
+ * value is the length of the path match including any implicit
+ * final '/'. For example, "http://me@example.com/path" is matched by
+ * "http://example.com" with a path length of 1.
+ *
+ * If there is a match and exactusermatch is not NULL, then
+ * *exactusermatch will be set to true if both url and url_prefix
+ * contained a user name or false if url_prefix did not have a
+ * user name. If there is no match *exactusermatch is left untouched.
+ */
+ int usermatched = 0;
+ int pathmatchlen;
+
+ if (!url || !url_prefix || !url->url || !url_prefix->url)
+ return 0;
+
+ /* check the scheme */
+ if (url_prefix->scheme_len != url->scheme_len ||
+ strncmp(url->url, url_prefix->url, url->scheme_len))
+ return 0; /* schemes do not match */
+
+ /* check the user name if url_prefix has one */
+ if (url_prefix->user_off) {
+ if (!url->user_off || url->user_len != url_prefix->user_len ||
+ strncmp(url->url + url->user_off,
+ url_prefix->url + url_prefix->user_off,
+ url->user_len))
+ return 0; /* url_prefix has a user but it's not a match */
+ usermatched = 1;
+ }
+
+ /* check the host and port */
+ if (url_prefix->host_len != url->host_len ||
+ strncmp(url->url + url->host_off,
+ url_prefix->url + url_prefix->host_off, url->host_len))
+ return 0; /* host names and/or ports do not match */
+
+ /* check the path */
+ pathmatchlen = url_match_prefix(
+ url->url + url->path_off,
+ url_prefix->url + url_prefix->path_off,
+ url_prefix->url_len - url_prefix->path_off);
+
+ if (pathmatchlen && exactusermatch)
+ *exactusermatch = usermatched;
+ return pathmatchlen;
+}
+
+int urlmatch_config_entry(const char *var, const char *value, void *cb)
+{
+ struct string_list_item *item;
+ struct urlmatch_config *collect = cb;
+ struct urlmatch_item *matched;
+ struct url_info *url = &collect->url;
+ const char *key, *dot;
+ struct strbuf synthkey = STRBUF_INIT;
+ size_t matched_len = 0;
+ int user_matched = 0;
+ int retval;
+
+ key = skip_prefix(var, collect->section);
+ if (!key || *(key++) != '.') {
+ if (collect->cascade_fn)
+ return collect->cascade_fn(var, value, cb);
+ return 0; /* not interested */
+ }
+ dot = strrchr(key, '.');
+ if (dot) {
+ char *config_url, *norm_url;
+ struct url_info norm_info;
+
+ config_url = xmemdupz(key, dot - key);
+ norm_url = url_normalize(config_url, &norm_info);
+ free(config_url);
+ if (!norm_url)
+ return 0;
+ matched_len = match_urls(url, &norm_info, &user_matched);
+ free(norm_url);
+ if (!matched_len)
+ return 0;
+ key = dot + 1;
+ }
+
+ if (collect->key && strcmp(key, collect->key))
+ return 0;
+
+ item = string_list_insert(&collect->vars, key);
+ if (!item->util) {
+ matched = xcalloc(1, sizeof(*matched));
+ item->util = matched;
+ } else {
+ matched = item->util;
+ /*
+ * Is our match shorter? Is our match the same
+ * length, and without user while the current
+ * candidate is with user? Then we cannot use it.
+ */
+ if (matched_len < matched->matched_len ||
+ ((matched_len == matched->matched_len) &&
+ (!user_matched && matched->user_matched)))
+ return 0;
+ /* Otherwise, replace it with this one. */
+ }
+
+ matched->matched_len = matched_len;
+ matched->user_matched = user_matched;
+ strbuf_addstr(&synthkey, collect->section);
+ strbuf_addch(&synthkey, '.');
+ strbuf_addstr(&synthkey, key);
+ retval = collect->collect_fn(synthkey.buf, value, collect->cb);
+
+ strbuf_release(&synthkey);
+ return retval;
+}
diff --git a/urlmatch.h b/urlmatch.h
new file mode 100644
index 0000000000..b461dfd3df
--- /dev/null
+++ b/urlmatch.h
@@ -0,0 +1,54 @@
+#ifndef URL_MATCH_H
+#include "string-list.h"
+
+struct url_info {
+ /* normalized url on success, must be freed, otherwise NULL */
+ char *url;
+ /* if !url, a brief reason for the failure, otherwise NULL */
+ const char *err;
+
+ /* the rest of the fields are only set if url != NULL */
+
+ size_t url_len; /* total length of url (which is now normalized) */
+ size_t scheme_len; /* length of scheme name (excluding final :) */
+ size_t user_off; /* offset into url to start of user name (0 => none) */
+ size_t user_len; /* length of user name; if user_off != 0 but
+ user_len == 0, an empty user name was given */
+ size_t passwd_off; /* offset into url to start of passwd (0 => none) */
+ size_t passwd_len; /* length of passwd; if passwd_off != 0 but
+ passwd_len == 0, an empty passwd was given */
+ size_t host_off; /* offset into url to start of host name (0 => none) */
+ size_t host_len; /* length of host name; this INCLUDES any ':portnum';
+ * file urls may have host_len == 0 */
+ size_t port_len; /* if a portnum is present (port_len != 0), it has
+ * this length (excluding the leading ':') at the
+ * end of the host name (always 0 for file urls) */
+ size_t path_off; /* offset into url to the start of the url path;
+ * this will always point to a '/' character
+ * after the url has been normalized */
+ size_t path_len; /* length of path portion excluding any trailing
+ * '?...' and '#...' portion; will always be >= 1 */
+};
+
+extern char *url_normalize(const char *, struct url_info *);
+extern int match_urls(const struct url_info *url, const struct url_info *url_prefix, int *exactusermatch);
+
+struct urlmatch_item {
+ size_t matched_len;
+ char user_matched;
+};
+
+struct urlmatch_config {
+ struct string_list vars;
+ struct url_info url;
+ const char *section;
+ const char *key;
+
+ void *cb;
+ int (*collect_fn)(const char *var, const char *value, void *cb);
+ int (*cascade_fn)(const char *var, const char *value, void *cb);
+};
+
+extern int urlmatch_config_entry(const char *var, const char *value, void *cb);
+
+#endif /* URL_MATCH_H */
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-26 15:00:37 +0000