config: parse http.<url>.<variable> using urlmatch

Use the urlmatch_config_entry() to wrap the underlying
http_options() two-level variable parser in order to set
http.<variable> to the value with the most specific URL in the
configuration.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Kyle J. McKay <mackyle@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

19 files changed, 309 insertions, 1 deletions

diff --git a/.gitignore b/.gitignore
index 6669bf0c6c..b8524bfe48 100644
--- a/.gitignore
+++ b/.gitignore
@@ -198,6 +198,7 @@
 /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 6e53fc5074..a81f3ab74e 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1513,6 +1513,51 @@ 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/Makefile b/Makefile
index 0f931a2030..2df742c24d 100644
--- a/Makefile
+++ b/Makefile
@@ -567,6 +567,7 @@ 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))
@@ -721,6 +722,7 @@ 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
@@ -868,6 +870,7 @@ 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/http.c b/http.c
index 37986f8252..5eda356fd9 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"
@@ -334,10 +335,20 @@ 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��𯿽
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‹Œ�Ž�
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›œ�žŸ
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/test-urlmatch-normalization.c b/test-urlmatch-normalization.c
new file mode 100644
index 0000000000..2603899bfe
--- /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(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(usage);
+
+	url1 = url_normalize(argv[1], NULL);
+	url2 = url_normalize(argv[2], NULL);
+	return (url1 && url2 && !strcmp(url1, url2)) ? 0 : 1;
+}