builtin: implement, document and test url-parse

.gitignore

@@ -174,6 +174,7 @@
 /git-update-server-info
 /git-upload-archive
 /git-upload-pack
+/git-url-parse
 /git-var
 /git-verify-commit
 /git-verify-pack

Documentation/git-url-parse.txt

@@ -0,0 +1,59 @@
+git-url-parse(1)
+================
+
+NAME
+----
+git-url-parse - Parse and extract git URL components
+
+SYNOPSIS
+--------
+[verse]
+'git url-parse' [<options>] [--] <url>...
+
+DESCRIPTION
+-----------
+
+Git supports many ways to specify URLs, some of them non-standard.
+For example, git supports the scp style [user@]host:[path] format.
+This command eases interoperability with git URLs by enabling the
+parsing and extraction of the components of all git URLs.
+
+OPTIONS
+-------
+
+-c <arg>::
+--component <arg>::
+ Extract the `<arg>` component from the given git URLs.
+ `<arg>` can be one of:
+ `protocol`, `user`, `password`, `host`, `port`, `path`.
+
+EXAMPLES
+--------
+
+* Print the host name:
++
+------------
+$ git url-parse --component host https://example.com/user/repo
+example.com
+------------
+
+* Print the path:
++
+------------
+$ git url-parse --component path https://example.com/user/repo
+/usr/repo
+$ git url-parse --component path example.com:~user/repo
+~user/repo
+$ git url-parse --component path example.com:user/repo
+/user/repo
+------------
+
+* Validate URLs without outputting anything:
++
+------------
+$ git url-parse https://example.com/user/repo example.com:~user/repo
+------------
+
+GIT
+---
+Part of the linkgit:git[1] suite

Makefile

@@ -1326,6 +1326,7 @@ BUILTIN_OBJS += builtin/update-ref.o
 BUILTIN_OBJS += builtin/update-server-info.o
 BUILTIN_OBJS += builtin/upload-archive.o
 BUILTIN_OBJS += builtin/upload-pack.o
+BUILTIN_OBJS += builtin/url-parse.o
 BUILTIN_OBJS += builtin/var.o
 BUILTIN_OBJS += builtin/verify-commit.o
 BUILTIN_OBJS += builtin/verify-pack.o

builtin.h

@@ -240,6 +240,7 @@ int cmd_update_server_info(int argc, const char **argv, const char *prefix);
 int cmd_upload_archive(int argc, const char **argv, const char *prefix);
 int cmd_upload_archive_writer(int argc, const char **argv, const char *prefix);
 int cmd_upload_pack(int argc, const char **argv, const char *prefix);
+int cmd_url_parse(int argc, const char **argv, const char *prefix);
 int cmd_var(int argc, const char **argv, const char *prefix);
 int cmd_verify_commit(int argc, const char **argv, const char *prefix);
 int cmd_verify_tag(int argc, const char **argv, const char *prefix);

builtin/url-parse.c

@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * url-parse - parses git URLs and extracts their components
+ *
+ * Copyright © 2024 Matheus Afonso Martins Moreira
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2.
+ */
+
+#include "builtin.h"
+#include "gettext.h"
+#include "parse-options.h"
+#include "urlmatch.h"
+
+static const char * const builtin_url_parse_usage[] = {
+ N_("git url-parse [<options>] [--] <url>..."),
+ NULL
+};
+
+static char *component_arg = NULL;
+
+static struct option builtin_url_parse_options[] = {
+ OPT_STRING('c', "component", &component_arg, "<component>", \
+ N_("which URL component to extract")),
+ OPT_END(),
+};
+
+enum url_component {
+ URL_NONE = 0,
+ URL_PROTOCOL,
+ URL_USER,
+ URL_PASSWORD,
+ URL_HOST,
+ URL_PORT,
+ URL_PATH,
+};
+
+static void parse_or_die(const char *url, struct url_info *info)
+{
+ if (url_parse(url, info)) {
+ return;
+ } else {
+ die("invalid git URL '%s', %s", url, info->err);
+ }
+}
+
+static enum url_component get_component_or_die(const char *arg)
+{
+ if (!strcmp("path", arg))
+ return URL_PATH;
+ if (!strcmp("host", arg))
+ return URL_HOST;
+ if (!strcmp("protocol", arg))
+ return URL_PROTOCOL;
+ if (!strcmp("user", arg))
+ return URL_USER;
+ if (!strcmp("password", arg))
+ return URL_PASSWORD;
+ if (!strcmp("port", arg))
+ return URL_PORT;
+ die("invalid git URL component '%s'", arg);
+}
+
+static char *extract(enum url_component component, struct url_info *info)
+{
+ size_t offset, length;
+
+ switch (component) {
+ case URL_PROTOCOL:
+ offset = 0;
+ length = info->scheme_len;
+ break;
+ case URL_USER:
+ offset = info->user_off;
+ length = info->user_len;
+ break;
+ case URL_PASSWORD:
+ offset = info->passwd_off;
+ length = info->passwd_len;
+ break;
+ case URL_HOST:
+ offset = info->host_off;
+ length = info->host_len;
+ break;
+ case URL_PORT:
+ offset = info->port_off;
+ length = info->port_len;
+ break;
+ case URL_PATH:
+ offset = info->path_off;
+ length = info->path_len;
+ break;
+ case URL_NONE:
+ return NULL;
+ }
+
+ return xstrndup(info->url + offset, length);
+}
+
+int cmd_url_parse(int argc, const char **argv, const char *prefix)
+{
+ struct url_info info;
+ enum url_component selected = URL_NONE;
+ char *extracted;
+ int i;
+
+ argc = parse_options(argc, argv, prefix,
+ builtin_url_parse_options,
+ builtin_url_parse_usage,
+ 0);
+
+ if (component_arg)
+ selected = get_component_or_die(component_arg);
+
+ for (i = 0; i < argc; ++i) {
+ parse_or_die(argv[i], &info);
+
+ if (selected != URL_NONE) {
+ extracted = extract(selected, &info);
+ if (extracted) {
+ puts(extracted);
+ free(extracted);
+ }
+ }
+
+ free(info.url);
+ }
+
+ return 0;
+}

command-list.txt

@@ -196,6 +196,7 @@ git-update-ref plumbingmanipulators
 git-update-server-info synchingrepositories
 git-upload-archive synchelpers
 git-upload-pack synchelpers
+git-url-parse plumbinginterrogators
 git-var plumbinginterrogators
 git-verify-commit ancillaryinterrogators
 git-verify-pack plumbinginterrogators

connect.c

@@ -693,14 +693,6 @@ enum protocol {
  PROTO_GIT
 };
 
-int url_is_local_not_ssh(const char *url)
-{
- const char *colon = strchr(url, ':');
- const char *slash = strchr(url, '/');
- return !colon || (slash && slash < colon) ||
- (has_dos_drive_prefix(url) && is_valid_path(url));
-}
-
 static const char *prot_name(enum protocol protocol)
 {
  switch (protocol) {

connect.h

@@ -13,7 +13,6 @@ int git_connection_is_socket(struct child_process *conn);
 int server_supports(const char *feature);
 int parse_feature_request(const char *features, const char *feature);
 const char *server_feature_value(const char *feature, size_t *len_ret);
-int url_is_local_not_ssh(const char *url);
 
 struct packet_reader;
 enum protocol_version discover_version(struct packet_reader *reader);

git.c

@@ -625,6 +625,7 @@ static struct cmd_struct commands[] = {
  { "upload-archive", cmd_upload_archive, NO_PARSEOPT },
  { "upload-archive--writer", cmd_upload_archive_writer, NO_PARSEOPT },
  { "upload-pack", cmd_upload_pack },
+ { "url-parse", cmd_url_parse, NO_PARSEOPT },
  { "var", cmd_var, RUN_SETUP_GENTLY | NO_PARSEOPT },
  { "verify-commit", cmd_verify_commit, RUN_SETUP },
  { "verify-pack", cmd_verify_pack },

remote.c

@@ -5,6 +5,7 @@
 #include "gettext.h"
 #include "hex.h"
 #include "remote.h"
+#include "url.h"
 #include "urlmatch.h"
 #include "refs.h"
 #include "refspec.h"