In order to perform sane URL matching for http.<url>.* options, http.c normalizes URLs before performing matches. A new test-url-normalize test program is introduced along with a new t5200-url-normalize.sh script to run the tests. Since the url_normalize function currently lives in http.c this test will be skipped if NO_CURL is defined since http.c is skipped in that case. Signed-off-by: Kyle J. McKay <mackyle@xxxxxxxxx> --- .gitignore | 1 + Makefile | 5 ++ t/t5200-url-normalize.sh | 182 +++++++++++++++++++++++++++++++++++++++++++++++ t/t5200/README | 9 +++ t/t5200/url-1 | 1 + t/t5200/url-10 | 1 + t/t5200/url-11 | 1 + t/t5200/url-2 | 1 + t/t5200/url-3 | 1 + t/t5200/url-4 | 1 + t/t5200/url-5 | 1 + t/t5200/url-6 | 1 + t/t5200/url-7 | 1 + t/t5200/url-8 | 1 + t/t5200/url-9 | 1 + test-url-normalize.c | 61 ++++++++++++++++ 16 files changed, 269 insertions(+) create mode 100755 t/t5200-url-normalize.sh create mode 100644 t/t5200/README create mode 100644 t/t5200/url-1 create mode 100644 t/t5200/url-10 create mode 100644 t/t5200/url-11 create mode 100644 t/t5200/url-2 create mode 100644 t/t5200/url-3 create mode 100644 t/t5200/url-4 create mode 100644 t/t5200/url-5 create mode 100644 t/t5200/url-6 create mode 100644 t/t5200/url-7 create mode 100644 t/t5200/url-8 create mode 100644 t/t5200/url-9 create mode 100644 test-url-normalize.c diff --git a/.gitignore b/.gitignore index 6669bf0..cd97e16 100644 --- a/.gitignore +++ b/.gitignore @@ -198,6 +198,7 @@ /test-string-list /test-subprocess /test-svn-fe +/test-url-normalize /test-wildmatch /common-cmds.h *.tar.gz diff --git a/Makefile b/Makefile index 0f931a2..f83879c 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-url-normalize TEST_PROGRAMS_NEED_X += test-wildmatch TEST_PROGRAMS = $(patsubst %,%$X,$(TEST_PROGRAMS_NEED_X)) @@ -2235,6 +2236,10 @@ test-parse-options$X: parse-options.o parse-options-cb.o test-svn-fe$X: vcs-svn/lib.a +test-url-normalize$X: test-url-normalize.o GIT-LDFLAGS $(GITLIBS) + $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \ + $(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT) + .PRECIOUS: $(TEST_OBJS) test-%$X: test-%.o GIT-LDFLAGS $(GITLIBS) diff --git a/t/t5200-url-normalize.sh b/t/t5200-url-normalize.sh new file mode 100755 index 0000000..12ac411 --- /dev/null +++ b/t/t5200-url-normalize.sh @@ -0,0 +1,182 @@ +#!/bin/sh + +test_description='url normalization' +. ./test-lib.sh + +if test -n "$NO_CURL"; then + skip_all='skipping test, git built without http support' + test_done +fi + +# The base name of the test url files +tu="$TEST_DIRECTORY/t5200/url" + +# Note that only file: URLs should be allowed without a host + +test_expect_success 'url scheme' ' + ! test-url-normalize "" && + ! test-url-normalize "_" && + ! test-url-normalize "scheme" && + ! test-url-normalize "scheme:" && + ! test-url-normalize "scheme:/" && + ! test-url-normalize "scheme://" && + ! test-url-normalize "file" && + ! test-url-normalize "file:" && + ! test-url-normalize "file:/" && + test-url-normalize "file://" && + ! test-url-normalize "://acme.co" && + ! test-url-normalize "x_test://acme.co" && + ! test-url-normalize "-test://acme.co" && + ! test-url-normalize "0test://acme.co" && + ! test-url-normalize "+test://acme.co" && + ! test-url-normalize ".test://acme.co" && + ! test-url-normalize "schem%6e://" && + test-url-normalize "x-Test+v1.0://acme.co" && + test "$(test-url-normalize -p "AbCdeF://x.Y")" = "abcdef://x.y/" +' + +test_expect_success 'url authority' ' + ! test-url-normalize "scheme://user:pass@" && + ! test-url-normalize "scheme://?" && + ! test-url-normalize "scheme://#" && + ! test-url-normalize "scheme:///" && + ! test-url-normalize "scheme://:" && + ! test-url-normalize "scheme://:555" && + test-url-normalize "file://user:pass@" && + test-url-normalize "file://?" && + test-url-normalize "file://#" && + test-url-normalize "file:///" && + test-url-normalize "file://:" && + ! test-url-normalize "file://:555" && + test-url-normalize "scheme://user:pass@host" && + test-url-normalize "scheme://@host" && + test-url-normalize "scheme://%00@host" && + ! test-url-normalize "scheme://%%@host" && + ! test-url-normalize "scheme://host_" && + test-url-normalize "scheme://user:pass@host/" && + test-url-normalize "scheme://@host/" && + test-url-normalize "scheme://host/" && + test-url-normalize "scheme://host?x" && + test-url-normalize "scheme://host#x" && + test-url-normalize "scheme://host/@" && + test-url-normalize "scheme://host?@x" && + test-url-normalize "scheme://host#@x" && + test-url-normalize "scheme://[::1]" && + test-url-normalize "scheme://[::1]/" && + ! test-url-normalize "scheme://hos%41/" && + test-url-normalize "scheme://[invalid....:/" && + test-url-normalize "scheme://invalid....:]/" && + ! test-url-normalize "scheme://invalid....:[/" && + ! test-url-normalize "scheme://invalid....:[" +' + +test_expect_success 'url port checks' ' + test-url-normalize "xyz://q@xxxxxxxxx:" && + test-url-normalize "xyz://q@xxxxxxxxx:456/" && + ! test-url-normalize "xyz://q@xxxxxxxxx:0" && + ! test-url-normalize "xyz://q@xxxxxxxxx:0000000" && + test-url-normalize "xyz://q@xxxxxxxxx:0000001?" && + test-url-normalize "xyz://q@xxxxxxxxx:065535#" && + test-url-normalize "xyz://q@xxxxxxxxx:65535" && + ! test-url-normalize "xyz://q@xxxxxxxxx:65536" && + ! test-url-normalize "xyz://q@xxxxxxxxx:99999" && + ! test-url-normalize "xyz://q@xxxxxxxxx:100000" && + ! test-url-normalize "xyz://q@xxxxxxxxx:100001" && + test-url-normalize "http://q@xxxxxxxxx:80"; && + test-url-normalize "https://q@xxxxxxxxx:443"; && + test-url-normalize "http://q@xxxxxxxxx:80/"; && + test-url-normalize "https://q@xxxxxxxxx:443?"; && + ! test-url-normalize "http://q@:8008"; && + ! test-url-normalize "http://:8080"; && + ! test-url-normalize "http://:"; && + test-url-normalize "xyz://q@xxxxxxxxx:456/" && + test-url-normalize "xyz://[::1]:456/" && + test-url-normalize "xyz://[::1]:/" && + ! test-url-normalize "xyz://[::1]:000/" && + ! test-url-normalize "xyz://[::1]:0%300/" && + ! test-url-normalize "xyz://[::1]:0x80/" && + ! test-url-normalize "xyz://[::1]:4294967297/" && + ! test-url-normalize "xyz://[::1]:030f/" +' + +test_expect_success 'url port normalization' ' + test "$(test-url-normalize -p "http://x:800";)" = "http://x:800/"; && + test "$(test-url-normalize -p "http://x:0800";)" = "http://x:800/"; && + test "$(test-url-normalize -p "http://x:00000800";)" = "http://x:800/"; && + test "$(test-url-normalize -p "http://x:065535";)" = "http://x:65535/"; && + test "$(test-url-normalize -p "http://x:1";)" = "http://x:1/"; && + test "$(test-url-normalize -p "http://x:80";)" = "http://x/"; && + test "$(test-url-normalize -p "http://x:080";)" = "http://x/"; && + test "$(test-url-normalize -p "http://x:000000080";)" = "http://x/"; && + test "$(test-url-normalize -p "https://x:443";)" = "https://x/"; && + test "$(test-url-normalize -p "https://x:0443";)" = "https://x/"; && + test "$(test-url-normalize -p "https://x:000000443";)" = "https://x/"; +' + +test_expect_success 'url general escapes' ' + ! test-url-normalize "http://x.y?%fg"; && + test "$(test-url-normalize -p "X://W/%7e%41^%3a")" = "x://w/~A%5E%3A" && + test "$(test-url-normalize -p "X://W/:/?#[]@")" = "x://w/:/?#[]@" && + test "$(test-url-normalize -p "X://W/$&()*+,;=")" = "x://w/$&()*+,;=" && + test "$(test-url-normalize -p "X://W/'\''")" = "x://w/'\''" && + test "$(test-url-normalize -p "X://W?'\!'")" = "x://w/?'\!'" +';#' + +test_expect_success 'url high-bit escapes' ' + test "$(test-url-normalize -p "$(cat "$tu-1")")" = "x://q/%01%02%03%04%05%06%07%08%0E%0F%10%11%12" && + test "$(test-url-normalize -p "$(cat "$tu-2")")" = "x://q/%13%14%15%16%17%18%19%1B%1C%1D%1E%1F%7F" && + test "$(test-url-normalize -p "$(cat "$tu-3")")" = "x://q/%80%81%82%83%84%85%86%87%88%89%8A%8B%8C%8D%8E%8F" && + test "$(test-url-normalize -p "$(cat "$tu-4")")" = "x://q/%90%91%92%93%94%95%96%97%98%99%9A%9B%9C%9D%9E%9F" && + test "$(test-url-normalize -p "$(cat "$tu-5")")" = "x://q/%A0%A1%A2%A3%A4%A5%A6%A7%A8%A9%AA%AB%AC%AD%AE%AF" && + test "$(test-url-normalize -p "$(cat "$tu-6")")" = "x://q/%B0%B1%B2%B3%B4%B5%B6%B7%B8%B9%BA%BB%BC%BD%BE%BF" && + test "$(test-url-normalize -p "$(cat "$tu-7")")" = "x://q/%C0%C1%C2%C3%C4%C5%C6%C7%C8%C9%CA%CB%CC%CD%CE%CF" && + test "$(test-url-normalize -p "$(cat "$tu-8")")" = "x://q/%D0%D1%D2%D3%D4%D5%D6%D7%D8%D9%DA%DB%DC%DD%DE%DF" && + test "$(test-url-normalize -p "$(cat "$tu-9")")" = "x://q/%E0%E1%E2%E3%E4%E5%E6%E7%E8%E9%EA%EB%EC%ED%EE%EF" && + test "$(test-url-normalize -p "$(cat "$tu-10")")" = "x://q/%F0%F1%F2%F3%F4%F5%F6%F7%F8%F9%FA%FB%FC%FD%FE%FF" && + test "$(test-url-normalize -p "$(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-url-normalize -p "x://%41%62(^):%70+d@foo")" = "x://Ab(%5E):p+d@foo/" +' + +test_expect_success 'url normalized lengths' ' + test "$(test-url-normalize -l "Http://%4d%65:%4d^%70@xxxxxxxx")" = 25 && + test "$(test-url-normalize -l "http://%41:%42@x.y/%61/";)" = 17 && + test "$(test-url-normalize -l "http://@x.y/^";)" = 15 +' + +test_expect_success 'url . and .. segments' ' + test "$(test-url-normalize -p "x://y/.")" = "x://y/" && + test "$(test-url-normalize -p "x://y/./")" = "x://y/" && + test "$(test-url-normalize -p "x://y/a/.")" = "x://y/a" && + test "$(test-url-normalize -p "x://y/a/./")" = "x://y/a/" && + test "$(test-url-normalize -p "x://y/.?")" = "x://y/?" && + test "$(test-url-normalize -p "x://y/./?")" = "x://y/?" && + test "$(test-url-normalize -p "x://y/a/.?")" = "x://y/a?" && + test "$(test-url-normalize -p "x://y/a/./?")" = "x://y/a/?" && + test "$(test-url-normalize -p "x://y/a/./b/.././../c")" = "x://y/c" && + test "$(test-url-normalize -p "x://y/a/./b/../.././c/")" = "x://y/c/" && + test "$(test-url-normalize -p "x://y/a/./b/.././../c/././.././.")" = "x://y/" && + ! test-url-normalize "x://y/a/./b/.././../c/././.././.." && + test "$(test-url-normalize -p "x://y/a/./?/././..")" = "x://y/a/?/././.." && + test "$(test-url-normalize -p "x://y/%2e/")" = "x://y/" && + test "$(test-url-normalize -p "x://y/%2E/")" = "x://y/" && + test "$(test-url-normalize -p "x://y/a/%2e./")" = "x://y/" && + test "$(test-url-normalize -p "x://y/b/.%2E/")" = "x://y/" && + test "$(test-url-normalize -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-url-normalize "httP://x" "Http://X/" && + test-url-normalize "Http://%4d%65:%4d^%70@xxxxxxxx" "hTTP://Me:%4D^p@xxxxxxxx:80/" && + ! test-url-normalize "https://@x.y/^"; "httpS://x.y:443/^" && + test-url-normalize "https://@x.y/^"; "httpS://@x.y:0443/^" && + test-url-normalize "https://@x.y/^/../abc"; "httpS://@x.y:0443/abc" && + test-url-normalize "https://@x.y/^/.."; "httpS://@x.y:0443/" +' + +test_done diff --git a/t/t5200/README b/t/t5200/README new file mode 100644 index 0000000..b908fe9 --- /dev/null +++ b/t/t5200/README @@ -0,0 +1,9 @@ +The 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. + +They are in test files in this directory rather than being +embedded in the test script for portability. diff --git a/t/t5200/url-1 b/t/t5200/url-1 new file mode 100644 index 0000000..519019c --- /dev/null +++ b/t/t5200/url-1 @@ -0,0 +1 @@ +x://q/ diff --git a/t/t5200/url-10 b/t/t5200/url-10 new file mode 100644 index 0000000..b9965de --- /dev/null +++ b/t/t5200/url-10 @@ -0,0 +1 @@ +x://q/ðñòóôõö÷øùúûüýþÿ diff --git a/t/t5200/url-11 b/t/t5200/url-11 new file mode 100644 index 0000000..f0a50f1 --- /dev/null +++ b/t/t5200/url-11 @@ -0,0 +1 @@ +x://q/Â?ß¿à ?�ð???𯿽 diff --git a/t/t5200/url-2 b/t/t5200/url-2 new file mode 100644 index 0000000..43334b0 --- /dev/null +++ b/t/t5200/url-2 @@ -0,0 +1 @@ +x://q/ diff --git a/t/t5200/url-3 b/t/t5200/url-3 new file mode 100644 index 0000000..7378c7b --- /dev/null +++ b/t/t5200/url-3 @@ -0,0 +1 @@ +x://q/???????????????? diff --git a/t/t5200/url-4 b/t/t5200/url-4 new file mode 100644 index 0000000..220b198 --- /dev/null +++ b/t/t5200/url-4 @@ -0,0 +1 @@ +x://q/???????????????? diff --git a/t/t5200/url-5 b/t/t5200/url-5 new file mode 100644 index 0000000..1ccd927 --- /dev/null +++ b/t/t5200/url-5 @@ -0,0 +1 @@ +x://q/ ¡¢£¤¥¦§¨©ª«¬®¯ diff --git a/t/t5200/url-6 b/t/t5200/url-6 new file mode 100644 index 0000000..e8283aa --- /dev/null +++ b/t/t5200/url-6 @@ -0,0 +1 @@ +x://q/°±²³´µ¶·¸¹º»¼½¾¿ diff --git a/t/t5200/url-7 b/t/t5200/url-7 new file mode 100644 index 0000000..fa7c10b --- /dev/null +++ b/t/t5200/url-7 @@ -0,0 +1 @@ +x://q/ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏ diff --git a/t/t5200/url-8 b/t/t5200/url-8 new file mode 100644 index 0000000..79a0ba8 --- /dev/null +++ b/t/t5200/url-8 @@ -0,0 +1 @@ +x://q/ÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞß diff --git a/t/t5200/url-9 b/t/t5200/url-9 new file mode 100644 index 0000000..8b44bec --- /dev/null +++ b/t/t5200/url-9 @@ -0,0 +1 @@ +x://q/àáâãäåæçèéêëìíîï diff --git a/test-url-normalize.c b/test-url-normalize.c new file mode 100644 index 0000000..d68312d --- /dev/null +++ b/test-url-normalize.c @@ -0,0 +1,61 @@ +#ifdef NO_CURL + +int main() +{ + return 125; +} + +#else /* !NO_CURL */ + +#include "http.c" + +#define url_normalize(u) http_options_url_normalize(u) + +int main(int argc, char **argv) +{ + const char *usage = "test-url-normalize [-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) { + url1 = url_normalize(argv[1]); + if (!url1) + return 1; + if (opt_p) + printf("%s\n", url1); + if (opt_l) + printf("%u\n", (unsigned)strlen(url1)); + return 0; + } + + if (opt_p || opt_l) + die(usage); + + url1 = url_normalize(argv[1]); + url2 = url_normalize(argv[2]); + return (url1 && url2 && !strcmp(url1, url2)) ? 0 : 1; +} + +#endif /* !NO_CURL */ -- 1.8.3 -- To unsubscribe from this list: send the line "unsubscribe git" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html